exo theme

EXO iOS app
2026-02-18 23:06:23 -05:00 · 2026-02-19 04:21:58 +05:00 · 2026-02-18 06:40:07 +05:00
100 changed files with 3639 additions and 1003 deletions
--- a/.mlx_typings/mlx_lm/models/glm_moe_dsa.pyi
+++ b/.mlx_typings/mlx_lm/models/glm_moe_dsa.pyi
@@ -1,46 +0,0 @@
-"""Type stubs for mlx_lm.models.glm_moe_dsa"""
-
-from dataclasses import dataclass
-from typing import Any, Dict, Optional
-
-from .base import BaseModelArgs
-from .deepseek_v32 import Model as DSV32Model
-
-@dataclass
-class ModelArgs(BaseModelArgs):
-    model_type: str
-    vocab_size: int
-    hidden_size: int
-    index_head_dim: int
-    index_n_heads: int
-    index_topk: int
-    intermediate_size: int
-    moe_intermediate_size: int
-    num_hidden_layers: int
-    num_attention_heads: int
-    num_key_value_heads: int
-    n_shared_experts: Optional[int]
-    n_routed_experts: Optional[int]
-    routed_scaling_factor: float
-    kv_lora_rank: int
-    q_lora_rank: int
-    qk_rope_head_dim: int
-    v_head_dim: int
-    qk_nope_head_dim: int
-    topk_method: str
-    scoring_func: str
-    norm_topk_prob: bool
-    n_group: int
-    topk_group: int
-    num_experts_per_tok: int
-    moe_layer_freq: int
-    first_k_dense_replace: int
-    max_position_embeddings: int
-    rms_norm_eps: float
-    rope_parameters: Dict[str, Any]
-    attention_bias: bool
-    rope_scaling: Dict[str, Any] | None
-    rope_theta: float | None
-
-class Model(DSV32Model):
-    def __init__(self, config: ModelArgs) -> None: ...
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -141,6 +141,12 @@ version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "76a2e8124351fda1ef8aaaa3bbd7ebbcb486bbcd4225aca0aa0d84bb2db8fecb"

+[[package]]
+name = "arrayvec"
+version = "0.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
+
 [[package]]
 name = "asn1-rs"
 version = "0.7.1"
@@ -298,6 +304,19 @@ version = "1.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "55248b47b0caf0546f7988906588779981c43bb1bc9d0c44087278f80cdb44ba"

+[[package]]
+name = "bigdecimal"
+version = "0.4.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "560f42649de9fa436b73517378a147ec21f6c997a546581df4b4b31677828934"
+dependencies = [
+ "autocfg",
+ "libm",
+ "num-bigint",
+ "num-integer",
+ "num-traits",
+]
+
 [[package]]
 name = "bimap"
 version = "0.6.3"
@@ -497,6 +516,15 @@ version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2f421161cb492475f1661ddc9815a745a1c894592070661180fdec3d4872e9c3"

+[[package]]
+name = "convert_case"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "633458d4ef8c78b72454de2d54fd6ab2e60f9e02be22f3c6104cdc8a4e0fceb9"
+dependencies = [
+ "unicode-segmentation",
+]
+
 [[package]]
 name = "core-foundation"
 version = "0.9.4"
@@ -718,6 +746,29 @@ dependencies = [
 "powerfmt",
 ]

+[[package]]
+name = "derive_more"
+version = "2.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10b768e943bed7bf2cab53df09f4bc34bfd217cdb57d971e769874c9a6710618"
+dependencies = [
+ "derive_more-impl",
+]
+
+[[package]]
+name = "derive_more-impl"
+version = "2.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6d286bfdaf75e988b4a78e013ecd79c581e06399ab53fbacd2d916c2f904f30b"
+dependencies = [
+ "convert_case",
+ "proc-macro2",
+ "quote",
+ "rustc_version",
+ "syn 2.0.111",
+ "unicode-xid",
+]
+
 [[package]]
 name = "digest"
 version = "0.10.7"
@@ -888,17 +939,22 @@ name = "exo_pyo3_bindings"
 version = "0.0.1"
 dependencies = [
 "delegate",
+ "derive_more",
 "env_logger",
 "extend",
 "futures",
+ "impl-trait-for-tuples",
 "libp2p",
 "log",
 "networking",
+ "once_cell",
 "pin-project",
 "pyo3",
 "pyo3-async-runtimes",
 "pyo3-log",
 "pyo3-stub-gen",
+ "thiserror 2.0.17",
+ "thread_local",
 "tokio",
 "util",
 ]
@@ -1584,6 +1640,17 @@ dependencies = [
 "xmltree",
 ]

+[[package]]
+name = "impl-trait-for-tuples"
+version = "0.2.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a0eb5a3343abf848c0984fe4604b2b105da9539376e24fc0a3b0007411ae4fd9"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.111",
+]
+
 [[package]]
 name = "indexmap"
 version = "2.12.1"
@@ -1762,6 +1829,12 @@ version = "0.2.178"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "37c93d8daa9d8a012fd8ab92f088405fb202ea0b6ab73ee2482ae66af4f42091"

+[[package]]
+name = "libm"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f9fbbcab51052fe104eb5e5d351cf728d30a5be1fe14d9be8a3b097481fb97de"
+
 [[package]]
 name = "libp2p"
 version = "0.56.0"
@@ -2751,13 +2824,16 @@ name = "networking"
 version = "0.0.1"
 dependencies = [
 "delegate",
+ "derive_more",
 "either",
 "extend",
 "futures",
 "futures-timer",
+ "impl-trait-for-tuples",
 "keccak-const",
 "libp2p",
 "log",
+ "thiserror 2.0.17",
 "tokio",
 "tracing-subscriber",
 "util",
@@ -2842,6 +2918,17 @@ dependencies = [
 "num-traits",
 ]

+[[package]]
+name = "num-rational"
+version = "0.4.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f83d14da390562dca69fc84082e73e548e1ad308d24accdedd2720017cb37824"
+dependencies = [
+ "num-bigint",
+ "num-integer",
+ "num-traits",
+]
+
 [[package]]
 name = "num-traits"
 version = "0.2.19"
@@ -3192,14 +3279,28 @@ version = "0.27.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ab53c047fcd1a1d2a8820fe84f05d6be69e9526be40cb03b73f86b6b03e6d87d"
 dependencies = [
+ "bigdecimal",
+ "either",
+ "hashbrown 0.16.1",
+ "indexmap",
 "indoc",
+ "inventory",
 "libc",
+ "lock_api",
 "memoffset",
+ "num-bigint",
+ "num-complex",
+ "num-rational",
+ "num-traits",
 "once_cell",
+ "ordered-float",
+ "parking_lot",
 "portable-atomic",
 "pyo3-build-config",
 "pyo3-ffi",
 "pyo3-macros",
+ "rust_decimal",
+ "smallvec",
 "unindent",
 ]

@@ -3640,6 +3741,16 @@ dependencies = [
 "tokio",
 ]

+[[package]]
+name = "rust_decimal"
+version = "1.39.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "35affe401787a9bd846712274d97654355d21b2a2c092a3139aabe31e9022282"
+dependencies = [
+ "arrayvec",
+ "num-traits",
+]
+
 [[package]]
 name = "rustc-hash"
 version = "1.1.0"
@@ -4504,12 +4615,24 @@ version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"

+[[package]]
+name = "unicode-segmentation"
+version = "1.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493"
+
 [[package]]
 name = "unicode-width"
 version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"

+[[package]]
+name = "unicode-xid"
+version = "0.2.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
+
 [[package]]
 name = "unicode_names2"
 version = "1.3.0"
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -26,21 +26,49 @@ opt-level = 3
 networking = { path = "rust/networking" }
 util = { path = "rust/util" }

+# Proc-macro authoring tools
+syn = "2.0"
+quote = "1.0"
+proc-macro2 = "1.0"
+darling = "0.20"
+
 # Macro dependecies
 extend = "1.2"
 delegate = "0.13"
+impl-trait-for-tuples = "0.2"
+clap = "4.5"
+derive_more = { version = "2.0.1", features = ["display"] }
 pin-project = "1"

 # Utility dependencies
+itertools = "0.14"
+thiserror = "2"
+internment = "0.8"
+recursion = "0.5"
+regex = "1.11"
+once_cell = "1.21"
+thread_local = "1.1"
+bon = "3.4"
+generativity = "1.1"
+anyhow = "1.0"
 keccak-const = "0.2"

+# Functional generics/lenses frameworks
+frunk_core = "0.4"
+frunk = "0.4"
+frunk_utils = "0.2"
+frunk-enum-core = "0.3"
+
 # Async dependencies
 tokio = "1.46"
 futures = "0.3"
+futures-util = "0.3"
 futures-timer = "3.0"

 # Data structures
 either = "1.15"
+ordered-float = "5.0"
+ahash = "0.8"

 # Tracing/logging
 log = "0.4"
--- a/README.md
+++ b/README.md
@@ -72,23 +72,16 @@ There are two ways to run exo:

 ### Run from Source (macOS)

-If you have [Nix](https://nixos.org/) installed, you can skip most of the steps below and run exo directly (after accepting the Cachix cache):
-
-```bash
-nix run .#exo
-```
-
 **Prerequisites:**
- [Xcode](https://developer.apple.com/xcode/) (provides the Metal ToolChain required for MLX compilation)
 - [brew](https://github.com/Homebrew/brew) (for simple package management on macOS)
-
+  
  ```bash
  /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
  ```
 - [uv](https://github.com/astral-sh/uv) (for Python dependency management)
 - [macmon](https://github.com/vladkens/macmon) (for hardware monitoring on Apple Silicon)
 - [node](https://github.com/nodejs/node) (for building the dashboard)
-
+  
  ```bash
  brew install uv macmon node
  ```
--- a/app/EXO-iOS/EXO-iOS.xcodeproj/project.pbxproj
+++ b/app/EXO-iOS/EXO-iOS.xcodeproj/project.pbxproj
@@ -0,0 +1,628 @@
+// !$*UTF8*$!
+{
+	archiveVersion = 1;
+	classes = {
+	};
+	objectVersion = 77;
+	objects = {
+
+/* Begin PBXBuildFile section */
+		E09D17522F44F359009C51A3 /* MLXLLM in Frameworks */ = {isa = PBXBuildFile; productRef = E09D17512F44F359009C51A3 /* MLXLLM */; };
+		E09D17542F44F359009C51A3 /* MLXLMCommon in Frameworks */ = {isa = PBXBuildFile; productRef = E09D17532F44F359009C51A3 /* MLXLMCommon */; };
+/* End PBXBuildFile section */
+
+/* Begin PBXContainerItemProxy section */
+		E09D167D2F44CA20009C51A3 /* PBXContainerItemProxy */ = {
+			isa = PBXContainerItemProxy;
+			containerPortal = E09D16672F44CA1E009C51A3 /* Project object */;
+			proxyType = 1;
+			remoteGlobalIDString = E09D166E2F44CA1E009C51A3;
+			remoteInfo = "EXO-iOS";
+		};
+		E09D16872F44CA20009C51A3 /* PBXContainerItemProxy */ = {
+			isa = PBXContainerItemProxy;
+			containerPortal = E09D16672F44CA1E009C51A3 /* Project object */;
+			proxyType = 1;
+			remoteGlobalIDString = E09D166E2F44CA1E009C51A3;
+			remoteInfo = "EXO-iOS";
+		};
+/* End PBXContainerItemProxy section */
+
+/* Begin PBXFileReference section */
+		E09D166F2F44CA1E009C51A3 /* EXO-iOS.app */ = {isa = PBXFileReference; explicitFileType = wrapper.application; includeInIndex = 0; path = "EXO-iOS.app"; sourceTree = BUILT_PRODUCTS_DIR; };
+		E09D167C2F44CA20009C51A3 /* EXO-iOSTests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = "EXO-iOSTests.xctest"; sourceTree = BUILT_PRODUCTS_DIR; };
+		E09D16862F44CA20009C51A3 /* EXO-iOSUITests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = "EXO-iOSUITests.xctest"; sourceTree = BUILT_PRODUCTS_DIR; };
+/* End PBXFileReference section */
+
+/* Begin PBXFileSystemSynchronizedBuildFileExceptionSet section */
+		E09D169A2F44CA20009C51A3 /* Exceptions for "EXO-iOS" folder in "EXO-iOS" target */ = {
+			isa = PBXFileSystemSynchronizedBuildFileExceptionSet;
+			membershipExceptions = (
+				Info.plist,
+			);
+			target = E09D166E2F44CA1E009C51A3 /* EXO-iOS */;
+		};
+/* End PBXFileSystemSynchronizedBuildFileExceptionSet section */
+
+/* Begin PBXFileSystemSynchronizedRootGroup section */
+		E09D16712F44CA1E009C51A3 /* EXO-iOS */ = {
+			isa = PBXFileSystemSynchronizedRootGroup;
+			exceptions = (
+				E09D169A2F44CA20009C51A3 /* Exceptions for "EXO-iOS" folder in "EXO-iOS" target */,
+			);
+			path = "EXO-iOS";
+			sourceTree = "<group>";
+		};
+		E09D167F2F44CA20009C51A3 /* EXO-iOSTests */ = {
+			isa = PBXFileSystemSynchronizedRootGroup;
+			path = "EXO-iOSTests";
+			sourceTree = "<group>";
+		};
+		E09D16892F44CA20009C51A3 /* EXO-iOSUITests */ = {
+			isa = PBXFileSystemSynchronizedRootGroup;
+			path = "EXO-iOSUITests";
+			sourceTree = "<group>";
+		};
+/* End PBXFileSystemSynchronizedRootGroup section */
+
+/* Begin PBXFrameworksBuildPhase section */
+		E09D166C2F44CA1E009C51A3 /* Frameworks */ = {
+			isa = PBXFrameworksBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+				E09D17542F44F359009C51A3 /* MLXLMCommon in Frameworks */,
+				E09D17522F44F359009C51A3 /* MLXLLM in Frameworks */,
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E09D16792F44CA20009C51A3 /* Frameworks */ = {
+			isa = PBXFrameworksBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E09D16832F44CA20009C51A3 /* Frameworks */ = {
+			isa = PBXFrameworksBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+/* End PBXFrameworksBuildPhase section */
+
+/* Begin PBXGroup section */
+		E09D16662F44CA1E009C51A3 = {
+			isa = PBXGroup;
+			children = (
+				E09D16712F44CA1E009C51A3 /* EXO-iOS */,
+				E09D167F2F44CA20009C51A3 /* EXO-iOSTests */,
+				E09D16892F44CA20009C51A3 /* EXO-iOSUITests */,
+				E09D16702F44CA1E009C51A3 /* Products */,
+			);
+			sourceTree = "<group>";
+		};
+		E09D16702F44CA1E009C51A3 /* Products */ = {
+			isa = PBXGroup;
+			children = (
+				E09D166F2F44CA1E009C51A3 /* EXO-iOS.app */,
+				E09D167C2F44CA20009C51A3 /* EXO-iOSTests.xctest */,
+				E09D16862F44CA20009C51A3 /* EXO-iOSUITests.xctest */,
+			);
+			name = Products;
+			sourceTree = "<group>";
+		};
+/* End PBXGroup section */
+
+/* Begin PBXNativeTarget section */
+		E09D166E2F44CA1E009C51A3 /* EXO-iOS */ = {
+			isa = PBXNativeTarget;
+			buildConfigurationList = E09D16902F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOS" */;
+			buildPhases = (
+				E09D166B2F44CA1E009C51A3 /* Sources */,
+				E09D166C2F44CA1E009C51A3 /* Frameworks */,
+				E09D166D2F44CA1E009C51A3 /* Resources */,
+			);
+			buildRules = (
+			);
+			dependencies = (
+			);
+			fileSystemSynchronizedGroups = (
+				E09D16712F44CA1E009C51A3 /* EXO-iOS */,
+			);
+			name = "EXO-iOS";
+			packageProductDependencies = (
+				E09D17512F44F359009C51A3 /* MLXLLM */,
+				E09D17532F44F359009C51A3 /* MLXLMCommon */,
+			);
+			productName = "EXO-iOS";
+			productReference = E09D166F2F44CA1E009C51A3 /* EXO-iOS.app */;
+			productType = "com.apple.product-type.application";
+		};
+		E09D167B2F44CA20009C51A3 /* EXO-iOSTests */ = {
+			isa = PBXNativeTarget;
+			buildConfigurationList = E09D16932F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOSTests" */;
+			buildPhases = (
+				E09D16782F44CA20009C51A3 /* Sources */,
+				E09D16792F44CA20009C51A3 /* Frameworks */,
+				E09D167A2F44CA20009C51A3 /* Resources */,
+			);
+			buildRules = (
+			);
+			dependencies = (
+				E09D167E2F44CA20009C51A3 /* PBXTargetDependency */,
+			);
+			fileSystemSynchronizedGroups = (
+				E09D167F2F44CA20009C51A3 /* EXO-iOSTests */,
+			);
+			name = "EXO-iOSTests";
+			packageProductDependencies = (
+			);
+			productName = "EXO-iOSTests";
+			productReference = E09D167C2F44CA20009C51A3 /* EXO-iOSTests.xctest */;
+			productType = "com.apple.product-type.bundle.unit-test";
+		};
+		E09D16852F44CA20009C51A3 /* EXO-iOSUITests */ = {
+			isa = PBXNativeTarget;
+			buildConfigurationList = E09D16962F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOSUITests" */;
+			buildPhases = (
+				E09D16822F44CA20009C51A3 /* Sources */,
+				E09D16832F44CA20009C51A3 /* Frameworks */,
+				E09D16842F44CA20009C51A3 /* Resources */,
+			);
+			buildRules = (
+			);
+			dependencies = (
+				E09D16882F44CA20009C51A3 /* PBXTargetDependency */,
+			);
+			fileSystemSynchronizedGroups = (
+				E09D16892F44CA20009C51A3 /* EXO-iOSUITests */,
+			);
+			name = "EXO-iOSUITests";
+			packageProductDependencies = (
+			);
+			productName = "EXO-iOSUITests";
+			productReference = E09D16862F44CA20009C51A3 /* EXO-iOSUITests.xctest */;
+			productType = "com.apple.product-type.bundle.ui-testing";
+		};
+/* End PBXNativeTarget section */
+
+/* Begin PBXProject section */
+		E09D16672F44CA1E009C51A3 /* Project object */ = {
+			isa = PBXProject;
+			attributes = {
+				BuildIndependentTargetsInParallel = 1;
+				LastSwiftUpdateCheck = 2620;
+				LastUpgradeCheck = 2620;
+				TargetAttributes = {
+					E09D166E2F44CA1E009C51A3 = {
+						CreatedOnToolsVersion = 26.2;
+					};
+					E09D167B2F44CA20009C51A3 = {
+						CreatedOnToolsVersion = 26.2;
+						TestTargetID = E09D166E2F44CA1E009C51A3;
+					};
+					E09D16852F44CA20009C51A3 = {
+						CreatedOnToolsVersion = 26.2;
+						TestTargetID = E09D166E2F44CA1E009C51A3;
+					};
+				};
+			};
+			buildConfigurationList = E09D166A2F44CA1E009C51A3 /* Build configuration list for PBXProject "EXO-iOS" */;
+			developmentRegion = en;
+			hasScannedForEncodings = 0;
+			knownRegions = (
+				en,
+				Base,
+			);
+			mainGroup = E09D16662F44CA1E009C51A3;
+			minimizedProjectReferenceProxies = 1;
+			packageReferences = (
+				E09D17502F44F359009C51A3 /* XCRemoteSwiftPackageReference "mlx-swift-lm" */,
+			);
+			preferredProjectObjectVersion = 77;
+			productRefGroup = E09D16702F44CA1E009C51A3 /* Products */;
+			projectDirPath = "";
+			projectRoot = "";
+			targets = (
+				E09D166E2F44CA1E009C51A3 /* EXO-iOS */,
+				E09D167B2F44CA20009C51A3 /* EXO-iOSTests */,
+				E09D16852F44CA20009C51A3 /* EXO-iOSUITests */,
+			);
+		};
+/* End PBXProject section */
+
+/* Begin PBXResourcesBuildPhase section */
+		E09D166D2F44CA1E009C51A3 /* Resources */ = {
+			isa = PBXResourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E09D167A2F44CA20009C51A3 /* Resources */ = {
+			isa = PBXResourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E09D16842F44CA20009C51A3 /* Resources */ = {
+			isa = PBXResourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+/* End PBXResourcesBuildPhase section */
+
+/* Begin PBXSourcesBuildPhase section */
+		E09D166B2F44CA1E009C51A3 /* Sources */ = {
+			isa = PBXSourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E09D16782F44CA20009C51A3 /* Sources */ = {
+			isa = PBXSourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+		E09D16822F44CA20009C51A3 /* Sources */ = {
+			isa = PBXSourcesBuildPhase;
+			buildActionMask = 2147483647;
+			files = (
+			);
+			runOnlyForDeploymentPostprocessing = 0;
+		};
+/* End PBXSourcesBuildPhase section */
+
+/* Begin PBXTargetDependency section */
+		E09D167E2F44CA20009C51A3 /* PBXTargetDependency */ = {
+			isa = PBXTargetDependency;
+			target = E09D166E2F44CA1E009C51A3 /* EXO-iOS */;
+			targetProxy = E09D167D2F44CA20009C51A3 /* PBXContainerItemProxy */;
+		};
+		E09D16882F44CA20009C51A3 /* PBXTargetDependency */ = {
+			isa = PBXTargetDependency;
+			target = E09D166E2F44CA1E009C51A3 /* EXO-iOS */;
+			targetProxy = E09D16872F44CA20009C51A3 /* PBXContainerItemProxy */;
+		};
+/* End PBXTargetDependency section */
+
+/* Begin XCBuildConfiguration section */
+		E09D168E2F44CA20009C51A3 /* Debug */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				ALWAYS_SEARCH_USER_PATHS = NO;
+				ASSETCATALOG_COMPILER_GENERATE_SWIFT_ASSET_SYMBOL_EXTENSIONS = YES;
+				CLANG_ANALYZER_NONNULL = YES;
+				CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
+				CLANG_CXX_LANGUAGE_STANDARD = "gnu++20";
+				CLANG_ENABLE_MODULES = YES;
+				CLANG_ENABLE_OBJC_ARC = YES;
+				CLANG_ENABLE_OBJC_WEAK = YES;
+				CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
+				CLANG_WARN_BOOL_CONVERSION = YES;
+				CLANG_WARN_COMMA = YES;
+				CLANG_WARN_CONSTANT_CONVERSION = YES;
+				CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
+				CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
+				CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
+				CLANG_WARN_EMPTY_BODY = YES;
+				CLANG_WARN_ENUM_CONVERSION = YES;
+				CLANG_WARN_INFINITE_RECURSION = YES;
+				CLANG_WARN_INT_CONVERSION = YES;
+				CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
+				CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
+				CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
+				CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
+				CLANG_WARN_QUOTED_INCLUDE_IN_FRAMEWORK_HEADER = YES;
+				CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
+				CLANG_WARN_STRICT_PROTOTYPES = YES;
+				CLANG_WARN_SUSPICIOUS_MOVE = YES;
+				CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
+				CLANG_WARN_UNREACHABLE_CODE = YES;
+				CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
+				COPY_PHASE_STRIP = NO;
+				DEBUG_INFORMATION_FORMAT = dwarf;
+				ENABLE_STRICT_OBJC_MSGSEND = YES;
+				ENABLE_TESTABILITY = YES;
+				ENABLE_USER_SCRIPT_SANDBOXING = YES;
+				GCC_C_LANGUAGE_STANDARD = gnu17;
+				GCC_DYNAMIC_NO_PIC = NO;
+				GCC_NO_COMMON_BLOCKS = YES;
+				GCC_OPTIMIZATION_LEVEL = 0;
+				GCC_PREPROCESSOR_DEFINITIONS = (
+					"DEBUG=1",
+					"$(inherited)",
+				);
+				GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
+				GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
+				GCC_WARN_UNDECLARED_SELECTOR = YES;
+				GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
+				GCC_WARN_UNUSED_FUNCTION = YES;
+				GCC_WARN_UNUSED_VARIABLE = YES;
+				IPHONEOS_DEPLOYMENT_TARGET = 26.2;
+				LOCALIZATION_PREFERS_STRING_CATALOGS = YES;
+				MTL_ENABLE_DEBUG_INFO = INCLUDE_SOURCE;
+				MTL_FAST_MATH = YES;
+				ONLY_ACTIVE_ARCH = YES;
+				SDKROOT = iphoneos;
+				SWIFT_ACTIVE_COMPILATION_CONDITIONS = "DEBUG $(inherited)";
+				SWIFT_OPTIMIZATION_LEVEL = "-Onone";
+			};
+			name = Debug;
+		};
+		E09D168F2F44CA20009C51A3 /* Release */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				ALWAYS_SEARCH_USER_PATHS = NO;
+				ASSETCATALOG_COMPILER_GENERATE_SWIFT_ASSET_SYMBOL_EXTENSIONS = YES;
+				CLANG_ANALYZER_NONNULL = YES;
+				CLANG_ANALYZER_NUMBER_OBJECT_CONVERSION = YES_AGGRESSIVE;
+				CLANG_CXX_LANGUAGE_STANDARD = "gnu++20";
+				CLANG_ENABLE_MODULES = YES;
+				CLANG_ENABLE_OBJC_ARC = YES;
+				CLANG_ENABLE_OBJC_WEAK = YES;
+				CLANG_WARN_BLOCK_CAPTURE_AUTORELEASING = YES;
+				CLANG_WARN_BOOL_CONVERSION = YES;
+				CLANG_WARN_COMMA = YES;
+				CLANG_WARN_CONSTANT_CONVERSION = YES;
+				CLANG_WARN_DEPRECATED_OBJC_IMPLEMENTATIONS = YES;
+				CLANG_WARN_DIRECT_OBJC_ISA_USAGE = YES_ERROR;
+				CLANG_WARN_DOCUMENTATION_COMMENTS = YES;
+				CLANG_WARN_EMPTY_BODY = YES;
+				CLANG_WARN_ENUM_CONVERSION = YES;
+				CLANG_WARN_INFINITE_RECURSION = YES;
+				CLANG_WARN_INT_CONVERSION = YES;
+				CLANG_WARN_NON_LITERAL_NULL_CONVERSION = YES;
+				CLANG_WARN_OBJC_IMPLICIT_RETAIN_SELF = YES;
+				CLANG_WARN_OBJC_LITERAL_CONVERSION = YES;
+				CLANG_WARN_OBJC_ROOT_CLASS = YES_ERROR;
+				CLANG_WARN_QUOTED_INCLUDE_IN_FRAMEWORK_HEADER = YES;
+				CLANG_WARN_RANGE_LOOP_ANALYSIS = YES;
+				CLANG_WARN_STRICT_PROTOTYPES = YES;
+				CLANG_WARN_SUSPICIOUS_MOVE = YES;
+				CLANG_WARN_UNGUARDED_AVAILABILITY = YES_AGGRESSIVE;
+				CLANG_WARN_UNREACHABLE_CODE = YES;
+				CLANG_WARN__DUPLICATE_METHOD_MATCH = YES;
+				COPY_PHASE_STRIP = NO;
+				DEBUG_INFORMATION_FORMAT = "dwarf-with-dsym";
+				ENABLE_NS_ASSERTIONS = NO;
+				ENABLE_STRICT_OBJC_MSGSEND = YES;
+				ENABLE_USER_SCRIPT_SANDBOXING = YES;
+				GCC_C_LANGUAGE_STANDARD = gnu17;
+				GCC_NO_COMMON_BLOCKS = YES;
+				GCC_WARN_64_TO_32_BIT_CONVERSION = YES;
+				GCC_WARN_ABOUT_RETURN_TYPE = YES_ERROR;
+				GCC_WARN_UNDECLARED_SELECTOR = YES;
+				GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE;
+				GCC_WARN_UNUSED_FUNCTION = YES;
+				GCC_WARN_UNUSED_VARIABLE = YES;
+				IPHONEOS_DEPLOYMENT_TARGET = 26.2;
+				LOCALIZATION_PREFERS_STRING_CATALOGS = YES;
+				MTL_ENABLE_DEBUG_INFO = NO;
+				MTL_FAST_MATH = YES;
+				SDKROOT = iphoneos;
+				SWIFT_COMPILATION_MODE = wholemodule;
+				VALIDATE_PRODUCT = YES;
+			};
+			name = Release;
+		};
+		E09D16912F44CA20009C51A3 /* Debug */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
+				ASSETCATALOG_COMPILER_GLOBAL_ACCENT_COLOR_NAME = AccentColor;
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				DEVELOPMENT_TEAM = 3M3M67U93M;
+				ENABLE_PREVIEWS = YES;
+				GENERATE_INFOPLIST_FILE = YES;
+				INFOPLIST_FILE = "EXO-iOS/Info.plist";
+				INFOPLIST_KEY_UIApplicationSceneManifest_Generation = YES;
+				INFOPLIST_KEY_UIApplicationSupportsIndirectInputEvents = YES;
+				INFOPLIST_KEY_UILaunchScreen_Generation = YES;
+				INFOPLIST_KEY_UISupportedInterfaceOrientations_iPad = "UIInterfaceOrientationPortrait UIInterfaceOrientationPortraitUpsideDown UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight";
+				INFOPLIST_KEY_UISupportedInterfaceOrientations_iPhone = "UIInterfaceOrientationPortrait UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight";
+				LD_RUNPATH_SEARCH_PATHS = (
+					"$(inherited)",
+					"@executable_path/Frameworks",
+				);
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOS";
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				STRING_CATALOG_GENERATE_SYMBOLS = YES;
+				SWIFT_APPROACHABLE_CONCURRENCY = YES;
+				SWIFT_DEFAULT_ACTOR_ISOLATION = MainActor;
+				SWIFT_EMIT_LOC_STRINGS = YES;
+				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
+				SWIFT_VERSION = 5.0;
+				TARGETED_DEVICE_FAMILY = "1,2";
+			};
+			name = Debug;
+		};
+		E09D16922F44CA20009C51A3 /* Release */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				ASSETCATALOG_COMPILER_APPICON_NAME = AppIcon;
+				ASSETCATALOG_COMPILER_GLOBAL_ACCENT_COLOR_NAME = AccentColor;
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				DEVELOPMENT_TEAM = 3M3M67U93M;
+				ENABLE_PREVIEWS = YES;
+				GENERATE_INFOPLIST_FILE = YES;
+				INFOPLIST_FILE = "EXO-iOS/Info.plist";
+				INFOPLIST_KEY_UIApplicationSceneManifest_Generation = YES;
+				INFOPLIST_KEY_UIApplicationSupportsIndirectInputEvents = YES;
+				INFOPLIST_KEY_UILaunchScreen_Generation = YES;
+				INFOPLIST_KEY_UISupportedInterfaceOrientations_iPad = "UIInterfaceOrientationPortrait UIInterfaceOrientationPortraitUpsideDown UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight";
+				INFOPLIST_KEY_UISupportedInterfaceOrientations_iPhone = "UIInterfaceOrientationPortrait UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight";
+				LD_RUNPATH_SEARCH_PATHS = (
+					"$(inherited)",
+					"@executable_path/Frameworks",
+				);
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOS";
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				STRING_CATALOG_GENERATE_SYMBOLS = YES;
+				SWIFT_APPROACHABLE_CONCURRENCY = YES;
+				SWIFT_DEFAULT_ACTOR_ISOLATION = MainActor;
+				SWIFT_EMIT_LOC_STRINGS = YES;
+				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
+				SWIFT_VERSION = 5.0;
+				TARGETED_DEVICE_FAMILY = "1,2";
+			};
+			name = Release;
+		};
+		E09D16942F44CA20009C51A3 /* Debug */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				BUNDLE_LOADER = "$(TEST_HOST)";
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				GENERATE_INFOPLIST_FILE = YES;
+				IPHONEOS_DEPLOYMENT_TARGET = 26.2;
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOSTests";
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				STRING_CATALOG_GENERATE_SYMBOLS = NO;
+				SWIFT_APPROACHABLE_CONCURRENCY = YES;
+				SWIFT_EMIT_LOC_STRINGS = NO;
+				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
+				SWIFT_VERSION = 5.0;
+				TARGETED_DEVICE_FAMILY = "1,2";
+				TEST_HOST = "$(BUILT_PRODUCTS_DIR)/EXO-iOS.app/$(BUNDLE_EXECUTABLE_FOLDER_PATH)/EXO-iOS";
+			};
+			name = Debug;
+		};
+		E09D16952F44CA20009C51A3 /* Release */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				BUNDLE_LOADER = "$(TEST_HOST)";
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				GENERATE_INFOPLIST_FILE = YES;
+				IPHONEOS_DEPLOYMENT_TARGET = 26.2;
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOSTests";
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				STRING_CATALOG_GENERATE_SYMBOLS = NO;
+				SWIFT_APPROACHABLE_CONCURRENCY = YES;
+				SWIFT_EMIT_LOC_STRINGS = NO;
+				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
+				SWIFT_VERSION = 5.0;
+				TARGETED_DEVICE_FAMILY = "1,2";
+				TEST_HOST = "$(BUILT_PRODUCTS_DIR)/EXO-iOS.app/$(BUNDLE_EXECUTABLE_FOLDER_PATH)/EXO-iOS";
+			};
+			name = Release;
+		};
+		E09D16972F44CA20009C51A3 /* Debug */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				GENERATE_INFOPLIST_FILE = YES;
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOSUITests";
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				STRING_CATALOG_GENERATE_SYMBOLS = NO;
+				SWIFT_APPROACHABLE_CONCURRENCY = YES;
+				SWIFT_EMIT_LOC_STRINGS = NO;
+				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
+				SWIFT_VERSION = 5.0;
+				TARGETED_DEVICE_FAMILY = "1,2";
+				TEST_TARGET_NAME = "EXO-iOS";
+			};
+			name = Debug;
+		};
+		E09D16982F44CA20009C51A3 /* Release */ = {
+			isa = XCBuildConfiguration;
+			buildSettings = {
+				CODE_SIGN_STYLE = Automatic;
+				CURRENT_PROJECT_VERSION = 1;
+				GENERATE_INFOPLIST_FILE = YES;
+				MARKETING_VERSION = 1.0;
+				PRODUCT_BUNDLE_IDENTIFIER = "com.exo.EXO-iOSUITests";
+				PRODUCT_NAME = "$(TARGET_NAME)";
+				STRING_CATALOG_GENERATE_SYMBOLS = NO;
+				SWIFT_APPROACHABLE_CONCURRENCY = YES;
+				SWIFT_EMIT_LOC_STRINGS = NO;
+				SWIFT_UPCOMING_FEATURE_MEMBER_IMPORT_VISIBILITY = YES;
+				SWIFT_VERSION = 5.0;
+				TARGETED_DEVICE_FAMILY = "1,2";
+				TEST_TARGET_NAME = "EXO-iOS";
+			};
+			name = Release;
+		};
+/* End XCBuildConfiguration section */
+
+/* Begin XCConfigurationList section */
+		E09D166A2F44CA1E009C51A3 /* Build configuration list for PBXProject "EXO-iOS" */ = {
+			isa = XCConfigurationList;
+			buildConfigurations = (
+				E09D168E2F44CA20009C51A3 /* Debug */,
+				E09D168F2F44CA20009C51A3 /* Release */,
+			);
+			defaultConfigurationIsVisible = 0;
+			defaultConfigurationName = Release;
+		};
+		E09D16902F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOS" */ = {
+			isa = XCConfigurationList;
+			buildConfigurations = (
+				E09D16912F44CA20009C51A3 /* Debug */,
+				E09D16922F44CA20009C51A3 /* Release */,
+			);
+			defaultConfigurationIsVisible = 0;
+			defaultConfigurationName = Release;
+		};
+		E09D16932F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOSTests" */ = {
+			isa = XCConfigurationList;
+			buildConfigurations = (
+				E09D16942F44CA20009C51A3 /* Debug */,
+				E09D16952F44CA20009C51A3 /* Release */,
+			);
+			defaultConfigurationIsVisible = 0;
+			defaultConfigurationName = Release;
+		};
+		E09D16962F44CA20009C51A3 /* Build configuration list for PBXNativeTarget "EXO-iOSUITests" */ = {
+			isa = XCConfigurationList;
+			buildConfigurations = (
+				E09D16972F44CA20009C51A3 /* Debug */,
+				E09D16982F44CA20009C51A3 /* Release */,
+			);
+			defaultConfigurationIsVisible = 0;
+			defaultConfigurationName = Release;
+		};
+/* End XCConfigurationList section */
+
+/* Begin XCRemoteSwiftPackageReference section */
+		E09D17502F44F359009C51A3 /* XCRemoteSwiftPackageReference "mlx-swift-lm" */ = {
+			isa = XCRemoteSwiftPackageReference;
+			repositoryURL = "https://github.com/ml-explore/mlx-swift-lm";
+			requirement = {
+				kind = upToNextMajorVersion;
+				minimumVersion = 2.30.3;
+			};
+		};
+/* End XCRemoteSwiftPackageReference section */
+
+/* Begin XCSwiftPackageProductDependency section */
+		E09D17512F44F359009C51A3 /* MLXLLM */ = {
+			isa = XCSwiftPackageProductDependency;
+			package = E09D17502F44F359009C51A3 /* XCRemoteSwiftPackageReference "mlx-swift-lm" */;
+			productName = MLXLLM;
+		};
+		E09D17532F44F359009C51A3 /* MLXLMCommon */ = {
+			isa = XCSwiftPackageProductDependency;
+			package = E09D17502F44F359009C51A3 /* XCRemoteSwiftPackageReference "mlx-swift-lm" */;
+			productName = MLXLMCommon;
+		};
+/* End XCSwiftPackageProductDependency section */
+	};
+	rootObject = E09D16672F44CA1E009C51A3 /* Project object */;
+}
--- a/app/EXO-iOS/EXO-iOS.xcodeproj/project.xcworkspace/contents.xcworkspacedata
+++ b/app/EXO-iOS/EXO-iOS.xcodeproj/project.xcworkspace/contents.xcworkspacedata
@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<Workspace
+   version = "1.0">
+   <FileRef
+      location = "self:">
+   </FileRef>
+</Workspace>
--- a/app/EXO-iOS/EXO-iOS.xcodeproj/project.xcworkspace/xcshareddata/swiftpm/Package.resolved
+++ b/app/EXO-iOS/EXO-iOS.xcodeproj/project.xcworkspace/xcshareddata/swiftpm/Package.resolved
@@ -0,0 +1,60 @@
+{
+  "originHash" : "facc0ac7c70363ea20f6cd1235de91dea6b06f0d00190946045a6c8ae753abc2",
+  "pins" : [
+    {
+      "identity" : "mlx-swift",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/ml-explore/mlx-swift",
+      "state" : {
+        "revision" : "6ba4827fb82c97d012eec9ab4b2de21f85c3b33d",
+        "version" : "0.30.6"
+      }
+    },
+    {
+      "identity" : "mlx-swift-lm",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/ml-explore/mlx-swift-lm",
+      "state" : {
+        "revision" : "360c5052b81cc154b04ee0933597a4ad6db4b8ae",
+        "version" : "2.30.3"
+      }
+    },
+    {
+      "identity" : "swift-collections",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/apple/swift-collections.git",
+      "state" : {
+        "revision" : "7b847a3b7008b2dc2f47ca3110d8c782fb2e5c7e",
+        "version" : "1.3.0"
+      }
+    },
+    {
+      "identity" : "swift-jinja",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/huggingface/swift-jinja.git",
+      "state" : {
+        "revision" : "d81197f35f41445bc10e94600795e68c6f5e94b0",
+        "version" : "2.3.1"
+      }
+    },
+    {
+      "identity" : "swift-numerics",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/apple/swift-numerics",
+      "state" : {
+        "revision" : "0c0290ff6b24942dadb83a929ffaaa1481df04a2",
+        "version" : "1.1.1"
+      }
+    },
+    {
+      "identity" : "swift-transformers",
+      "kind" : "remoteSourceControl",
+      "location" : "https://github.com/huggingface/swift-transformers",
+      "state" : {
+        "revision" : "573e5c9036c2f136b3a8a071da8e8907322403d0",
+        "version" : "1.1.6"
+      }
+    }
+  ],
+  "version" : 3
+}
--- a/app/EXO-iOS/EXO-iOS/Assets.xcassets/AccentColor.colorset/Contents.json
+++ b/app/EXO-iOS/EXO-iOS/Assets.xcassets/AccentColor.colorset/Contents.json
@@ -0,0 +1,20 @@
+{
+  "colors" : [
+    {
+      "color" : {
+        "color-space" : "srgb",
+        "components" : {
+          "alpha" : "1.000",
+          "blue" : "0x00",
+          "green" : "0xD7",
+          "red" : "0xFF"
+        }
+      },
+      "idiom" : "universal"
+    }
+  ],
+  "info" : {
+    "author" : "xcode",
+    "version" : 1
+  }
+}
--- a/app/EXO-iOS/EXO-iOS/Assets.xcassets/AppIcon.appiconset/AppIcon.png
+++ b/app/EXO-iOS/EXO-iOS/Assets.xcassets/AppIcon.appiconset/AppIcon.png
--- a/app/EXO-iOS/EXO-iOS/Assets.xcassets/AppIcon.appiconset/Contents.json
+++ b/app/EXO-iOS/EXO-iOS/Assets.xcassets/AppIcon.appiconset/Contents.json
@@ -0,0 +1,38 @@
+{
+  "images" : [
+    {
+      "filename" : "AppIcon.png",
+      "idiom" : "universal",
+      "platform" : "ios",
+      "size" : "1024x1024"
+    },
+    {
+      "appearances" : [
+        {
+          "appearance" : "luminosity",
+          "value" : "dark"
+        }
+      ],
+      "filename" : "AppIcon.png",
+      "idiom" : "universal",
+      "platform" : "ios",
+      "size" : "1024x1024"
+    },
+    {
+      "appearances" : [
+        {
+          "appearance" : "luminosity",
+          "value" : "tinted"
+        }
+      ],
+      "filename" : "AppIcon.png",
+      "idiom" : "universal",
+      "platform" : "ios",
+      "size" : "1024x1024"
+    }
+  ],
+  "info" : {
+    "author" : "xcode",
+    "version" : 1
+  }
+}
--- a/app/EXO-iOS/EXO-iOS/Assets.xcassets/Contents.json
+++ b/app/EXO-iOS/EXO-iOS/Assets.xcassets/Contents.json
@@ -0,0 +1,6 @@
+{
+  "info" : {
+    "author" : "xcode",
+    "version" : 1
+  }
+}
--- a/app/EXO-iOS/EXO-iOS/Assets.xcassets/ExoLogo.imageset/Contents.json
+++ b/app/EXO-iOS/EXO-iOS/Assets.xcassets/ExoLogo.imageset/Contents.json
@@ -0,0 +1,21 @@
+{
+  "images" : [
+    {
+      "filename" : "exo-logo.png",
+      "idiom" : "universal",
+      "scale" : "1x"
+    },
+    {
+      "idiom" : "universal",
+      "scale" : "2x"
+    },
+    {
+      "idiom" : "universal",
+      "scale" : "3x"
+    }
+  ],
+  "info" : {
+    "author" : "xcode",
+    "version" : 1
+  }
+}
--- a/app/EXO-iOS/EXO-iOS/Assets.xcassets/ExoLogo.imageset/exo-logo.png
+++ b/app/EXO-iOS/EXO-iOS/Assets.xcassets/ExoLogo.imageset/exo-logo.png
--- a/app/EXO-iOS/EXO-iOS/EXO-iOS.entitlements
+++ b/app/EXO-iOS/EXO-iOS/EXO-iOS.entitlements
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+	<key>com.apple.developer.kernel.increased-memory-limit</key>
+	<true/>
+</dict>
+</plist>
--- a/app/EXO-iOS/EXO-iOS/EXO_iOSApp.swift
+++ b/app/EXO-iOS/EXO-iOS/EXO_iOSApp.swift
@@ -0,0 +1,67 @@
+import SwiftUI
+import UIKit
+
+@main
+struct EXO_iOSApp: App {
+    @State private var clusterService = ClusterService()
+    @State private var discoveryService = DiscoveryService()
+    @State private var localInferenceService = LocalInferenceService()
+    @State private var chatService: ChatService?
+
+    init() {
+        let darkGray = UIColor(red: 0x1F / 255.0, green: 0x1F / 255.0, blue: 0x1F / 255.0, alpha: 1)
+        let yellow = UIColor(red: 0xFF / 255.0, green: 0xD7 / 255.0, blue: 0x00 / 255.0, alpha: 1)
+
+        let navAppearance = UINavigationBarAppearance()
+        navAppearance.configureWithOpaqueBackground()
+        navAppearance.backgroundColor = darkGray
+        navAppearance.titleTextAttributes = [
+            .foregroundColor: yellow,
+            .font: UIFont.monospacedSystemFont(ofSize: 17, weight: .semibold),
+        ]
+        navAppearance.largeTitleTextAttributes = [
+            .foregroundColor: yellow,
+            .font: UIFont.monospacedSystemFont(ofSize: 34, weight: .bold),
+        ]
+
+        UINavigationBar.appearance().standardAppearance = navAppearance
+        UINavigationBar.appearance().compactAppearance = navAppearance
+        UINavigationBar.appearance().scrollEdgeAppearance = navAppearance
+        UINavigationBar.appearance().tintColor = yellow
+    }
+
+    var body: some Scene {
+        WindowGroup {
+            if let chatService {
+                RootView()
+                    .environment(clusterService)
+                    .environment(discoveryService)
+                    .environment(chatService)
+                    .environment(localInferenceService)
+                    .preferredColorScheme(.dark)
+                    .task {
+                        await clusterService.attemptAutoReconnect()
+                        discoveryService.startBrowsing()
+                        await localInferenceService.prepareModel()
+                    }
+                    .onChange(of: discoveryService.discoveredClusters) { _, clusters in
+                        guard !clusterService.isConnected,
+                            case .disconnected = clusterService.connectionState,
+                            let first = clusters.first
+                        else { return }
+                        Task {
+                            await clusterService.connectToDiscoveredCluster(
+                                first, using: discoveryService)
+                        }
+                    }
+            } else {
+                Color.exoBlack.onAppear {
+                    chatService = ChatService(
+                        clusterService: clusterService,
+                        localInferenceService: localInferenceService
+                    )
+                }
+            }
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Info.plist
+++ b/app/EXO-iOS/EXO-iOS/Info.plist
@@ -0,0 +1,19 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
+<plist version="1.0">
+<dict>
+	<key>UIUserInterfaceStyle</key>
+	<string>Dark</string>
+	<key>CFBundleDisplayName</key>
+	<string>EXO</string>
+	<key>NSLocalNetworkUsageDescription</key>
+	<string>EXO needs local network access to connect to your EXO cluster.</string>
+	<key>NSBonjourServices</key>
+	<array>
+		<string>_exo._tcp</string>
+		<string>_p2p._tcp</string>
+		<string>_p2p._udp</string>
+		<string>_libp2p._udp</string>
+	</array>
+</dict>
+</plist>
--- a/app/EXO-iOS/EXO-iOS/Models/ChatCompletionTypes.swift
+++ b/app/EXO-iOS/EXO-iOS/Models/ChatCompletionTypes.swift
@@ -0,0 +1,129 @@
+import Foundation
+
+// MARK: - Request
+
+struct ChatCompletionRequest: Encodable {
+    let model: String
+    let messages: [ChatCompletionMessageParam]
+    let stream: Bool
+    let maxTokens: Int?
+    let temperature: Double?
+
+    enum CodingKeys: String, CodingKey {
+        case model, messages, stream, temperature
+        case maxTokens = "max_tokens"
+    }
+}
+
+struct ChatCompletionMessageParam: Encodable {
+    let role: String
+    let content: String
+}
+
+// MARK: - Streaming Response
+
+struct ChatCompletionChunk: Decodable {
+    let id: String
+    let model: String?
+    let choices: [StreamingChoice]
+    let usage: ChunkUsage?
+
+    init(id: String, model: String?, choices: [StreamingChoice], usage: ChunkUsage?) {
+        self.id = id
+        self.model = model
+        self.choices = choices
+        self.usage = usage
+    }
+}
+
+struct StreamingChoice: Decodable {
+    let index: Int
+    let delta: Delta
+    let finishReason: String?
+
+    enum CodingKeys: String, CodingKey {
+        case index, delta
+        case finishReason = "finish_reason"
+    }
+
+    init(index: Int, delta: Delta, finishReason: String?) {
+        self.index = index
+        self.delta = delta
+        self.finishReason = finishReason
+    }
+}
+
+struct Delta: Decodable {
+    let role: String?
+    let content: String?
+
+    init(role: String?, content: String?) {
+        self.role = role
+        self.content = content
+    }
+}
+
+struct ChunkUsage: Decodable {
+    let promptTokens: Int?
+    let completionTokens: Int?
+    let totalTokens: Int?
+
+    enum CodingKeys: String, CodingKey {
+        case promptTokens = "prompt_tokens"
+        case completionTokens = "completion_tokens"
+        case totalTokens = "total_tokens"
+    }
+
+    init(promptTokens: Int?, completionTokens: Int?, totalTokens: Int?) {
+        self.promptTokens = promptTokens
+        self.completionTokens = completionTokens
+        self.totalTokens = totalTokens
+    }
+}
+
+// MARK: - Non-Streaming Response
+
+struct ChatCompletionResponse: Decodable {
+    let id: String
+    let model: String?
+    let choices: [ResponseChoice]
+}
+
+struct ResponseChoice: Decodable {
+    let index: Int
+    let message: ResponseMessage
+    let finishReason: String?
+
+    enum CodingKeys: String, CodingKey {
+        case index, message
+        case finishReason = "finish_reason"
+    }
+}
+
+struct ResponseMessage: Decodable {
+    let role: String?
+    let content: String?
+}
+
+// MARK: - Models List
+
+struct ModelListResponse: Decodable {
+    let data: [ModelInfo]
+}
+
+struct ModelInfo: Decodable, Identifiable {
+    let id: String
+    let name: String?
+}
+
+// MARK: - Error
+
+struct APIErrorResponse: Decodable {
+    let error: APIErrorInfo
+}
+
+struct APIErrorInfo: Decodable {
+    let message: String
+    let type: String?
+    let code: Int?
+}
--- a/app/EXO-iOS/EXO-iOS/Models/ChatMessage.swift
+++ b/app/EXO-iOS/EXO-iOS/Models/ChatMessage.swift
@@ -0,0 +1,26 @@
+import Foundation
+
+struct ChatMessage: Identifiable, Equatable {
+    let id: UUID
+    let role: Role
+    var content: String
+    let timestamp: Date
+    var isStreaming: Bool
+
+    enum Role: String, Codable {
+        case user
+        case assistant
+        case system
+    }
+
+    init(
+        id: UUID = UUID(), role: Role, content: String, timestamp: Date = Date(),
+        isStreaming: Bool = false
+    ) {
+        self.id = id
+        self.role = role
+        self.content = content
+        self.timestamp = timestamp
+        self.isStreaming = isStreaming
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Models/ConnectionInfo.swift
+++ b/app/EXO-iOS/EXO-iOS/Models/ConnectionInfo.swift
@@ -0,0 +1,11 @@
+import Foundation
+
+struct ConnectionInfo: Codable, Equatable {
+    let host: String
+    let port: Int
+    let nodeId: String?
+
+    var baseURL: URL { URL(string: "http://\(host):\(port)")! }
+
+    static let defaultPort = 52415
+}
--- a/app/EXO-iOS/EXO-iOS/Models/Conversation.swift
+++ b/app/EXO-iOS/EXO-iOS/Models/Conversation.swift
@@ -0,0 +1,34 @@
+import Foundation
+
+struct Conversation: Identifiable, Codable, Equatable {
+    let id: UUID
+    var title: String
+    var messages: [StoredMessage]
+    var modelId: String?
+    let createdAt: Date
+
+    init(
+        id: UUID = UUID(), title: String = "New Chat", messages: [StoredMessage] = [],
+        modelId: String? = nil, createdAt: Date = Date()
+    ) {
+        self.id = id
+        self.title = title
+        self.messages = messages
+        self.modelId = modelId
+        self.createdAt = createdAt
+    }
+}
+
+struct StoredMessage: Identifiable, Codable, Equatable {
+    let id: UUID
+    let role: String
+    var content: String
+    let timestamp: Date
+
+    init(id: UUID = UUID(), role: String, content: String, timestamp: Date = Date()) {
+        self.id = id
+        self.role = role
+        self.content = content
+        self.timestamp = timestamp
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Services/ChatService.swift
+++ b/app/EXO-iOS/EXO-iOS/Services/ChatService.swift
@@ -0,0 +1,227 @@
+import Foundation
+
+@Observable
+@MainActor
+final class ChatService {
+    var conversations: [Conversation] = []
+    var activeConversationId: UUID?
+    private(set) var isGenerating: Bool = false
+    private var currentGenerationTask: Task<Void, Never>?
+
+    private let clusterService: ClusterService
+    private let localInferenceService: LocalInferenceService
+
+    var canSendMessage: Bool {
+        clusterService.isConnected || localInferenceService.isAvailable
+    }
+
+    var activeConversation: Conversation? {
+        guard let id = activeConversationId else { return nil }
+        return conversations.first { $0.id == id }
+    }
+
+    var activeMessages: [ChatMessage] {
+        guard let conversation = activeConversation else { return [] }
+        return conversation.messages.map { stored in
+            ChatMessage(
+                id: stored.id,
+                role: ChatMessage.Role(rawValue: stored.role) ?? .user,
+                content: stored.content,
+                timestamp: stored.timestamp
+            )
+        }
+    }
+
+    init(clusterService: ClusterService, localInferenceService: LocalInferenceService) {
+        self.clusterService = clusterService
+        self.localInferenceService = localInferenceService
+        loadConversations()
+    }
+
+    // MARK: - Conversation Management
+
+    func createConversation(modelId: String? = nil) {
+        let conversation = Conversation(
+            modelId: modelId ?? clusterService.availableModels.first?.id)
+        conversations.insert(conversation, at: 0)
+        activeConversationId = conversation.id
+        saveConversations()
+    }
+
+    func deleteConversation(id: UUID) {
+        conversations.removeAll { $0.id == id }
+        if activeConversationId == id {
+            activeConversationId = conversations.first?.id
+        }
+        saveConversations()
+    }
+
+    func setActiveConversation(id: UUID) {
+        activeConversationId = id
+    }
+
+    func setModelForActiveConversation(_ modelId: String) {
+        guard let index = conversations.firstIndex(where: { $0.id == activeConversationId }) else {
+            return
+        }
+        conversations[index].modelId = modelId
+        saveConversations()
+    }
+
+    // MARK: - Messaging
+
+    func sendMessage(_ text: String) {
+        guard !text.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty else { return }
+
+        if activeConversation == nil {
+            createConversation()
+        }
+
+        guard let index = conversations.firstIndex(where: { $0.id == activeConversationId }) else {
+            return
+        }
+
+        let userMessage = StoredMessage(role: "user", content: text)
+        conversations[index].messages.append(userMessage)
+
+        if conversations[index].title == "New Chat" {
+            let preview = String(text.prefix(40))
+            conversations[index].title = preview + (text.count > 40 ? "..." : "")
+        }
+
+        let modelId: String
+        if clusterService.isConnected {
+            guard
+                let clusterId = conversations[index].modelId
+                    ?? clusterService.availableModels.first?.id
+            else {
+                let errorMessage = StoredMessage(
+                    role: "assistant", content: "No model selected. Please select a model first.")
+                conversations[index].messages.append(errorMessage)
+                saveConversations()
+                return
+            }
+            modelId = clusterId
+        } else if localInferenceService.isAvailable {
+            modelId = localInferenceService.defaultModelId
+        } else {
+            let errorMessage = StoredMessage(
+                role: "assistant",
+                content: "Not connected to a cluster and local model is not available.")
+            conversations[index].messages.append(errorMessage)
+            saveConversations()
+            return
+        }
+
+        conversations[index].modelId = modelId
+
+        let assistantMessageId = UUID()
+        let assistantMessage = StoredMessage(
+            id: assistantMessageId, role: "assistant", content: "", timestamp: Date())
+        conversations[index].messages.append(assistantMessage)
+
+        let messagesForAPI = conversations[index].messages.dropLast().map { stored in
+            ChatCompletionMessageParam(role: stored.role, content: stored.content)
+        }
+
+        let request = ChatCompletionRequest(
+            model: modelId,
+            messages: Array(messagesForAPI),
+            stream: true,
+            maxTokens: 4096,
+            temperature: nil
+        )
+
+        let conversationId = conversations[index].id
+
+        isGenerating = true
+        currentGenerationTask = Task { [weak self] in
+            guard let self else { return }
+            await self.performStreaming(
+                request: request, conversationId: conversationId,
+                assistantMessageId: assistantMessageId)
+        }
+
+        saveConversations()
+    }
+
+    func cancelGeneration() {
+        currentGenerationTask?.cancel()
+        currentGenerationTask = nil
+        localInferenceService.cancelGeneration()
+        isGenerating = false
+    }
+
+    // MARK: - Streaming
+
+    private func performStreaming(
+        request: ChatCompletionRequest, conversationId: UUID, assistantMessageId: UUID
+    ) async {
+        defer {
+            isGenerating = false
+            currentGenerationTask = nil
+            saveConversations()
+        }
+
+        do {
+            let stream =
+                clusterService.isConnected
+                ? clusterService.streamChatCompletion(request: request)
+                : localInferenceService.streamChatCompletion(request: request)
+            for try await chunk in stream {
+                guard !Task.isCancelled else { return }
+                guard let content = chunk.choices.first?.delta.content, !content.isEmpty else {
+                    continue
+                }
+
+                if let convIndex = conversations.firstIndex(where: { $0.id == conversationId }),
+                    let msgIndex = conversations[convIndex].messages.firstIndex(where: {
+                        $0.id == assistantMessageId
+                    })
+                {
+                    conversations[convIndex].messages[msgIndex].content += content
+                }
+            }
+        } catch {
+            if !Task.isCancelled {
+                if let convIndex = conversations.firstIndex(where: { $0.id == conversationId }),
+                    let msgIndex = conversations[convIndex].messages.firstIndex(where: {
+                        $0.id == assistantMessageId
+                    })
+                {
+                    if conversations[convIndex].messages[msgIndex].content.isEmpty {
+                        conversations[convIndex].messages[msgIndex].content =
+                            "Error: \(error.localizedDescription)"
+                    }
+                }
+            }
+        }
+    }
+
+    // MARK: - Persistence
+
+    private static var storageURL: URL {
+        let documents = FileManager.default.urls(for: .documentDirectory, in: .userDomainMask)
+            .first!
+        return documents.appendingPathComponent("exo_conversations.json")
+    }
+
+    private func saveConversations() {
+        do {
+            let data = try JSONEncoder().encode(conversations)
+            try data.write(to: Self.storageURL, options: .atomic)
+        } catch {
+            // Save failed silently
+        }
+    }
+
+    private func loadConversations() {
+        do {
+            let data = try Data(contentsOf: Self.storageURL)
+            conversations = try JSONDecoder().decode([Conversation].self, from: data)
+            activeConversationId = conversations.first?.id
+        } catch {
+            conversations = []
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Services/ClusterService.swift
+++ b/app/EXO-iOS/EXO-iOS/Services/ClusterService.swift
@@ -0,0 +1,200 @@
+import Foundation
+
+enum ConnectionState: Equatable {
+    case disconnected
+    case connecting
+    case connected(ConnectionInfo)
+}
+
+struct ModelOption: Identifiable, Equatable {
+    let id: String
+    let displayName: String
+}
+
+@Observable
+@MainActor
+final class ClusterService {
+    private(set) var connectionState: ConnectionState = .disconnected
+    private(set) var availableModels: [ModelOption] = []
+    private(set) var lastError: String?
+
+    private let session: URLSession
+    private let decoder: JSONDecoder
+    private var pollingTask: Task<Void, Never>?
+
+    private static let connectionInfoKey = "exo_last_connection_info"
+
+    var isConnected: Bool {
+        if case .connected = connectionState { return true }
+        return false
+    }
+
+    var currentConnection: ConnectionInfo? {
+        if case .connected(let info) = connectionState { return info }
+        return nil
+    }
+
+    init(session: URLSession = .shared) {
+        self.session = session
+        let decoder = JSONDecoder()
+        self.decoder = decoder
+    }
+
+    // MARK: - Connection
+
+    func connect(to info: ConnectionInfo) async {
+        connectionState = .connecting
+        lastError = nil
+
+        do {
+            let url = info.baseURL.appendingPathComponent("node_id")
+            var request = URLRequest(url: url)
+            request.timeoutInterval = 5
+            request.cachePolicy = .reloadIgnoringLocalCacheData
+            let (_, response) = try await session.data(for: request)
+
+            guard let httpResponse = response as? HTTPURLResponse,
+                (200..<300).contains(httpResponse.statusCode)
+            else {
+                throw URLError(.badServerResponse)
+            }
+
+            connectionState = .connected(info)
+            persistConnection(info)
+            startPolling()
+            await fetchModels(baseURL: info.baseURL)
+        } catch {
+            connectionState = .disconnected
+            lastError = "Could not connect to \(info.host):\(info.port)"
+        }
+    }
+
+    func connectToDiscoveredCluster(
+        _ cluster: DiscoveredCluster, using discoveryService: DiscoveryService
+    ) async {
+        guard case .disconnected = connectionState else { return }
+        connectionState = .connecting
+        lastError = nil
+
+        guard let info = await discoveryService.resolve(cluster) else {
+            connectionState = .disconnected
+            lastError = "Could not resolve \(cluster.name)"
+            return
+        }
+        connectionState = .disconnected  // reset so connect() can proceed
+        await connect(to: info)
+    }
+
+    func disconnect() {
+        stopPolling()
+        connectionState = .disconnected
+        availableModels = []
+        lastError = nil
+    }
+
+    func attemptAutoReconnect() async {
+        guard case .disconnected = connectionState,
+            let info = loadPersistedConnection()
+        else { return }
+        await connect(to: info)
+    }
+
+    // MARK: - Polling
+
+    private func startPolling(interval: TimeInterval = 2.0) {
+        stopPolling()
+        pollingTask = Task { [weak self] in
+            while !Task.isCancelled {
+                try? await Task.sleep(for: .seconds(interval))
+                guard let self, !Task.isCancelled else { return }
+                guard let connection = self.currentConnection else { return }
+                await self.fetchModels(baseURL: connection.baseURL)
+            }
+        }
+    }
+
+    private func stopPolling() {
+        pollingTask?.cancel()
+        pollingTask = nil
+    }
+
+    // MARK: - API
+
+    private func fetchModels(baseURL: URL) async {
+        do {
+            let url = baseURL.appendingPathComponent("models")
+            var request = URLRequest(url: url)
+            request.cachePolicy = .reloadIgnoringLocalCacheData
+            let (data, response) = try await session.data(for: request)
+
+            guard let httpResponse = response as? HTTPURLResponse,
+                (200..<300).contains(httpResponse.statusCode)
+            else { return }
+
+            let list = try decoder.decode(ModelListResponse.self, from: data)
+            availableModels = list.data.map {
+                ModelOption(id: $0.id, displayName: $0.name ?? $0.id)
+            }
+        } catch {
+            // Models fetch failed silently — will retry on next poll
+        }
+    }
+
+    func streamChatCompletion(request body: ChatCompletionRequest) -> AsyncThrowingStream<
+        ChatCompletionChunk, Error
+    > {
+        AsyncThrowingStream { continuation in
+            let task = Task { [weak self] in
+                guard let self, let connection = self.currentConnection else {
+                    continuation.finish(throwing: URLError(.notConnectedToInternet))
+                    return
+                }
+
+                do {
+                    let url = connection.baseURL.appendingPathComponent("v1/chat/completions")
+                    var request = URLRequest(url: url)
+                    request.httpMethod = "POST"
+                    request.setValue("application/json", forHTTPHeaderField: "Content-Type")
+                    request.httpBody = try JSONEncoder().encode(body)
+
+                    let (bytes, response) = try await self.session.bytes(for: request)
+
+                    guard let httpResponse = response as? HTTPURLResponse,
+                        (200..<300).contains(httpResponse.statusCode)
+                    else {
+                        continuation.finish(throwing: URLError(.badServerResponse))
+                        return
+                    }
+
+                    let parser = SSEStreamParser<ChatCompletionChunk>(
+                        bytes: bytes, decoder: self.decoder)
+                    for try await chunk in parser {
+                        continuation.yield(chunk)
+                    }
+                    continuation.finish()
+                } catch {
+                    continuation.finish(throwing: error)
+                }
+            }
+
+            continuation.onTermination = { _ in
+                task.cancel()
+            }
+        }
+    }
+
+    // MARK: - Persistence
+
+    private func persistConnection(_ info: ConnectionInfo) {
+        if let data = try? JSONEncoder().encode(info) {
+            UserDefaults.standard.set(data, forKey: Self.connectionInfoKey)
+        }
+    }
+
+    private func loadPersistedConnection() -> ConnectionInfo? {
+        guard let data = UserDefaults.standard.data(forKey: Self.connectionInfoKey) else {
+            return nil
+        }
+        return try? JSONDecoder().decode(ConnectionInfo.self, from: data)
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Services/DiscoveryService.swift
+++ b/app/EXO-iOS/EXO-iOS/Services/DiscoveryService.swift
@@ -0,0 +1,123 @@
+import Foundation
+import Network
+import os
+
+struct DiscoveredCluster: Identifiable, Equatable {
+    let id: String
+    let name: String
+    let endpoint: NWEndpoint
+
+    static func == (lhs: DiscoveredCluster, rhs: DiscoveredCluster) -> Bool {
+        lhs.id == rhs.id && lhs.name == rhs.name
+    }
+}
+
+@Observable
+@MainActor
+final class DiscoveryService {
+    private(set) var discoveredClusters: [DiscoveredCluster] = []
+    private(set) var isSearching = false
+
+    private var browser: NWBrowser?
+
+    func startBrowsing() {
+        guard browser == nil else { return }
+
+        let browser = NWBrowser(for: .bonjour(type: "_exo._tcp", domain: nil), using: .tcp)
+
+        browser.stateUpdateHandler = { [weak self] state in
+            guard let service = self else { return }
+            Task { @MainActor in
+                switch state {
+                case .ready:
+                    service.isSearching = true
+                case .failed, .cancelled:
+                    service.isSearching = false
+                default:
+                    break
+                }
+            }
+        }
+
+        browser.browseResultsChangedHandler = { [weak self] results, _ in
+            guard let service = self else { return }
+            Task { @MainActor in
+                service.discoveredClusters = results.compactMap { result in
+                    guard case .service(let name, _, _, _) = result.endpoint else {
+                        return nil
+                    }
+                    return DiscoveredCluster(
+                        id: name,
+                        name: name,
+                        endpoint: result.endpoint
+                    )
+                }
+            }
+        }
+
+        browser.start(queue: .main)
+        self.browser = browser
+    }
+
+    func stopBrowsing() {
+        browser?.cancel()
+        browser = nil
+        isSearching = false
+        discoveredClusters = []
+    }
+
+    /// Resolve a discovered Bonjour endpoint to an IP address and port, then return a ConnectionInfo.
+    func resolve(_ cluster: DiscoveredCluster) async -> ConnectionInfo? {
+        await withCheckedContinuation { continuation in
+            let didResume = OSAllocatedUnfairLock(initialState: false)
+            let connection = NWConnection(to: cluster.endpoint, using: .tcp)
+            connection.stateUpdateHandler = { state in
+                guard
+                    didResume.withLock({
+                        guard !$0 else { return false }
+                        $0 = true
+                        return true
+                    })
+                else { return }
+                switch state {
+                case .ready:
+                    if let innerEndpoint = connection.currentPath?.remoteEndpoint,
+                        case .hostPort(let host, let port) = innerEndpoint
+                    {
+                        var hostString: String
+                        switch host {
+                        case .ipv4(let addr):
+                            hostString = "\(addr)"
+                        case .ipv6(let addr):
+                            hostString = "\(addr)"
+                        case .name(let name, _):
+                            hostString = name
+                        @unknown default:
+                            hostString = "\(host)"
+                        }
+                        // Strip interface scope suffix (e.g. "%en0")
+                        if let pct = hostString.firstIndex(of: "%") {
+                            hostString = String(hostString[..<pct])
+                        }
+                        let info = ConnectionInfo(
+                            host: hostString,
+                            port: Int(port.rawValue),
+                            nodeId: nil
+                        )
+                        connection.cancel()
+                        continuation.resume(returning: info)
+                    } else {
+                        connection.cancel()
+                        continuation.resume(returning: nil)
+                    }
+                case .failed, .cancelled:
+                    continuation.resume(returning: nil)
+                default:
+                    // Not a terminal state — allow future callbacks
+                    didResume.withLock { $0 = false }
+                }
+            }
+            connection.start(queue: .global(qos: .userInitiated))
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Services/LocalInferenceService.swift
+++ b/app/EXO-iOS/EXO-iOS/Services/LocalInferenceService.swift
@@ -0,0 +1,201 @@
+import Foundation
+import MLXLLM
+import MLXLMCommon
+
+enum LocalModelState: Equatable {
+    case notDownloaded
+    case downloading(progress: Double)
+    case downloaded
+    case loading
+    case ready
+    case generating
+    case error(String)
+}
+
+@Observable
+@MainActor
+final class LocalInferenceService {
+    private(set) var modelState: LocalModelState = .notDownloaded
+    private var modelContainer: ModelContainer?
+    private var generationTask: Task<Void, Never>?
+
+    let defaultModelId = "mlx-community/Qwen3-0.6B-4bit"
+
+    private static let modelDownloadedKey = "exo_local_model_downloaded"
+
+    var isReady: Bool {
+        modelState == .ready
+    }
+
+    var isAvailable: Bool {
+        modelState == .ready || modelState == .generating
+    }
+
+    init() {
+        if UserDefaults.standard.bool(forKey: Self.modelDownloadedKey) {
+            modelState = .downloaded
+        }
+    }
+
+    // MARK: - Model Lifecycle
+
+    func prepareModel() async {
+        guard modelState == .notDownloaded || modelState == .downloaded else { return }
+
+        let wasDownloaded = modelState == .downloaded
+
+        if !wasDownloaded {
+            modelState = .downloading(progress: 0)
+        } else {
+            modelState = .loading
+        }
+
+        do {
+            let container = try await loadModelContainer(
+                id: defaultModelId
+            ) { [weak self] progress in
+                guard let self else { return }
+                Task { @MainActor in
+                    if case .downloading = self.modelState {
+                        self.modelState = .downloading(progress: progress.fractionCompleted)
+                    }
+                }
+            }
+
+            self.modelContainer = container
+            UserDefaults.standard.set(true, forKey: Self.modelDownloadedKey)
+            modelState = .ready
+        } catch {
+            modelState = .error(error.localizedDescription)
+        }
+    }
+
+    func unloadModel() {
+        cancelGeneration()
+        modelContainer = nil
+        modelState = .downloaded
+    }
+
+    // MARK: - Generation
+
+    func streamChatCompletion(request: ChatCompletionRequest) -> AsyncThrowingStream<
+        ChatCompletionChunk, Error
+    > {
+        AsyncThrowingStream { continuation in
+            let task = Task { [weak self] in
+                guard let self else {
+                    continuation.finish(throwing: LocalInferenceError.serviceUnavailable)
+                    return
+                }
+
+                guard let container = self.modelContainer else {
+                    continuation.finish(throwing: LocalInferenceError.modelNotLoaded)
+                    return
+                }
+
+                await MainActor.run {
+                    self.modelState = .generating
+                }
+
+                defer {
+                    Task { @MainActor [weak self] in
+                        if self?.modelState == .generating {
+                            self?.modelState = .ready
+                        }
+                    }
+                }
+
+                let chunkId = "local-\(UUID().uuidString)"
+
+                do {
+                    // Build Chat.Message array from the request
+                    var chatMessages: [Chat.Message] = []
+                    for msg in request.messages {
+                        switch msg.role {
+                        case "system":
+                            chatMessages.append(.system(msg.content))
+                        case "assistant":
+                            chatMessages.append(.assistant(msg.content))
+                        default:
+                            chatMessages.append(.user(msg.content))
+                        }
+                    }
+
+                    // Use ChatSession for streaming generation
+                    let session = ChatSession(
+                        container,
+                        history: chatMessages,
+                        generateParameters: GenerateParameters(
+                            maxTokens: request.maxTokens ?? 4096,
+                            temperature: Float(request.temperature ?? 0.7)
+                        )
+                    )
+
+                    // Stream with an empty prompt since history already contains the conversation
+                    let stream = session.streamResponse(to: "")
+                    for try await text in stream {
+                        if Task.isCancelled { break }
+
+                        let chunk = ChatCompletionChunk(
+                            id: chunkId,
+                            model: request.model,
+                            choices: [
+                                StreamingChoice(
+                                    index: 0,
+                                    delta: Delta(role: nil, content: text),
+                                    finishReason: nil
+                                )
+                            ],
+                            usage: nil
+                        )
+                        continuation.yield(chunk)
+                    }
+
+                    // Send final chunk with finish reason
+                    let finalChunk = ChatCompletionChunk(
+                        id: chunkId,
+                        model: request.model,
+                        choices: [
+                            StreamingChoice(
+                                index: 0,
+                                delta: Delta(role: nil, content: nil),
+                                finishReason: "stop"
+                            )
+                        ],
+                        usage: nil
+                    )
+                    continuation.yield(finalChunk)
+                    continuation.finish()
+                } catch {
+                    continuation.finish(throwing: error)
+                }
+            }
+
+            self.generationTask = task
+
+            continuation.onTermination = { _ in
+                task.cancel()
+            }
+        }
+    }
+
+    func cancelGeneration() {
+        generationTask?.cancel()
+        generationTask = nil
+        if modelState == .generating {
+            modelState = .ready
+        }
+    }
+}
+
+enum LocalInferenceError: LocalizedError {
+    case serviceUnavailable
+    case modelNotLoaded
+
+    var errorDescription: String? {
+        switch self {
+        case .serviceUnavailable: "Local inference service is unavailable"
+        case .modelNotLoaded: "Local model is not loaded"
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Services/SSEStreamParser.swift
+++ b/app/EXO-iOS/EXO-iOS/Services/SSEStreamParser.swift
@@ -0,0 +1,50 @@
+import Foundation
+
+struct SSEStreamParser<T: Decodable>: AsyncSequence {
+    typealias Element = T
+
+    let bytes: URLSession.AsyncBytes
+    let decoder: JSONDecoder
+
+    init(bytes: URLSession.AsyncBytes, decoder: JSONDecoder = JSONDecoder()) {
+        self.bytes = bytes
+        self.decoder = decoder
+    }
+
+    func makeAsyncIterator() -> AsyncIterator {
+        AsyncIterator(lines: bytes.lines, decoder: decoder)
+    }
+
+    struct AsyncIterator: AsyncIteratorProtocol {
+        var lines: AsyncLineSequence<URLSession.AsyncBytes>.AsyncIterator
+        let decoder: JSONDecoder
+
+        init(lines: AsyncLineSequence<URLSession.AsyncBytes>, decoder: JSONDecoder) {
+            self.lines = lines.makeAsyncIterator()
+            self.decoder = decoder
+        }
+
+        mutating func next() async throws -> T? {
+            while let line = try await lines.next() {
+                let trimmed = line.trimmingCharacters(in: .whitespaces)
+
+                guard trimmed.hasPrefix("data: ") else { continue }
+
+                let payload = String(trimmed.dropFirst(6))
+
+                if payload == "[DONE]" {
+                    return nil
+                }
+
+                guard let data = payload.data(using: .utf8) else { continue }
+
+                do {
+                    return try decoder.decode(T.self, from: data)
+                } catch {
+                    continue
+                }
+            }
+            return nil
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/Chat/ChatView.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/Chat/ChatView.swift
@@ -0,0 +1,203 @@
+import SwiftUI
+
+struct ChatView: View {
+    @Environment(ClusterService.self) private var clusterService
+    @Environment(ChatService.self) private var chatService
+    @Environment(LocalInferenceService.self) private var localInferenceService
+    @State private var inputText = ""
+    @State private var showModelSelector = false
+
+    var body: some View {
+        VStack(spacing: 0) {
+            modelBar
+
+            GradientDivider()
+
+            messageList
+
+            GradientDivider()
+
+            inputBar
+        }
+        .background(Color.exoBlack)
+        .sheet(isPresented: $showModelSelector) {
+            ModelSelectorView(
+                models: clusterService.availableModels,
+                selectedModelId: chatService.activeConversation?.modelId
+            ) { modelId in
+                chatService.setModelForActiveConversation(modelId)
+            }
+            .presentationBackground(Color.exoDarkGray)
+        }
+    }
+
+    // MARK: - Model Bar
+
+    private var useLocalModel: Bool {
+        !clusterService.isConnected && localInferenceService.isAvailable
+    }
+
+    private var modelBar: some View {
+        Button {
+            if !useLocalModel {
+                showModelSelector = true
+            }
+        } label: {
+            HStack {
+                Image(systemName: useLocalModel ? "iphone" : "cpu")
+                    .font(.exoCaption)
+                    .foregroundStyle(useLocalModel ? Color.exoYellow : Color.exoLightGray)
+
+                if useLocalModel {
+                    Text(localInferenceService.defaultModelId)
+                        .font(.exoSubheadline)
+                        .foregroundStyle(Color.exoForeground)
+                        .lineLimit(1)
+                } else if let modelId = chatService.activeConversation?.modelId {
+                    Text(modelId)
+                        .font(.exoSubheadline)
+                        .foregroundStyle(Color.exoForeground)
+                        .lineLimit(1)
+                } else {
+                    Text("SELECT MODEL")
+                        .font(.exoSubheadline)
+                        .tracking(1.5)
+                        .foregroundStyle(Color.exoLightGray)
+                }
+
+                Spacer()
+
+                if useLocalModel {
+                    Text("ON-DEVICE")
+                        .font(.exoCaption)
+                        .tracking(1)
+                        .foregroundStyle(Color.exoYellow)
+                        .padding(.horizontal, 6)
+                        .padding(.vertical, 2)
+                        .background(Color.exoYellow.opacity(0.15))
+                        .clipShape(Capsule())
+                } else {
+                    Image(systemName: "chevron.right")
+                        .font(.caption)
+                        .foregroundStyle(Color.exoLightGray)
+                }
+            }
+            .padding(.horizontal)
+            .padding(.vertical, 10)
+            .background(Color.exoDarkGray)
+        }
+        .tint(.primary)
+        .disabled(useLocalModel)
+    }
+
+    // MARK: - Messages
+
+    private var messageList: some View {
+        ScrollViewReader { proxy in
+            ScrollView {
+                LazyVStack(spacing: 12) {
+                    if chatService.activeMessages.isEmpty {
+                        emptyState
+                    } else {
+                        ForEach(chatService.activeMessages) { message in
+                            MessageBubbleView(message: message)
+                                .id(message.id)
+                        }
+                    }
+                }
+                .padding()
+            }
+            .background(Color.exoBlack)
+            .onChange(of: chatService.activeMessages.last?.content) {
+                if let lastId = chatService.activeMessages.last?.id {
+                    withAnimation(.easeOut(duration: 0.2)) {
+                        proxy.scrollTo(lastId, anchor: .bottom)
+                    }
+                }
+            }
+        }
+    }
+
+    private var emptyState: some View {
+        VStack(spacing: 16) {
+            Spacer(minLength: 80)
+
+            ZStack {
+                Circle()
+                    .stroke(Color.exoYellow.opacity(0.15), lineWidth: 1)
+                    .frame(width: 80, height: 80)
+                Circle()
+                    .stroke(Color.exoYellow.opacity(0.3), lineWidth: 1)
+                    .frame(width: 56, height: 56)
+                Circle()
+                    .fill(Color.exoYellow.opacity(0.15))
+                    .frame(width: 32, height: 32)
+                Circle()
+                    .fill(Color.exoYellow)
+                    .frame(width: 8, height: 8)
+                    .shadow(color: Color.exoYellow.opacity(0.6), radius: 6)
+            }
+
+            Text("AWAITING INPUT")
+                .font(.exoSubheadline)
+                .tracking(3)
+                .foregroundStyle(Color.exoLightGray)
+
+            Text("Send a message to begin.")
+                .font(.exoCaption)
+                .foregroundStyle(Color.exoLightGray.opacity(0.6))
+
+            Spacer(minLength: 80)
+        }
+        .padding()
+    }
+
+    // MARK: - Input
+
+    private var inputBar: some View {
+        HStack(alignment: .bottom, spacing: 8) {
+            TextField("Message...", text: $inputText, axis: .vertical)
+                .font(.exoBody)
+                .lineLimit(1...6)
+                .textFieldStyle(.plain)
+                .padding(10)
+                .background(Color.exoMediumGray)
+                .foregroundStyle(Color.exoForeground)
+                .clipShape(RoundedRectangle(cornerRadius: 8))
+
+            if chatService.isGenerating {
+                Button {
+                    chatService.cancelGeneration()
+                } label: {
+                    Image(systemName: "stop.circle.fill")
+                        .font(.title2)
+                        .foregroundStyle(Color.exoDestructive)
+                }
+            } else {
+                Button {
+                    let text = inputText
+                    inputText = ""
+                    chatService.sendMessage(text)
+                } label: {
+                    Text("SEND")
+                        .font(.exoMono(12, weight: .bold))
+                        .tracking(1)
+                        .foregroundStyle(canSend ? Color.exoBlack : Color.exoLightGray)
+                        .padding(.horizontal, 14)
+                        .padding(.vertical, 8)
+                        .background(canSend ? Color.exoYellow : Color.exoMediumGray)
+                        .clipShape(RoundedRectangle(cornerRadius: 8))
+                }
+                .disabled(!canSend)
+            }
+        }
+        .padding(.horizontal)
+        .padding(.vertical, 8)
+        .background(Color.exoDarkGray)
+    }
+
+    private var canSend: Bool {
+        !inputText.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
+            && (clusterService.isConnected || localInferenceService.isAvailable)
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/Chat/MessageBubbleView.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/Chat/MessageBubbleView.swift
@@ -0,0 +1,54 @@
+import SwiftUI
+
+struct MessageBubbleView: View {
+    let message: ChatMessage
+
+    private var isAssistant: Bool { message.role == .assistant }
+
+    var body: some View {
+        HStack {
+            if message.role == .user { Spacer(minLength: 48) }
+
+            VStack(alignment: isAssistant ? .leading : .trailing, spacing: 6) {
+                // Header
+                HStack(spacing: 4) {
+                    if isAssistant {
+                        Circle()
+                            .fill(Color.exoYellow)
+                            .frame(width: 6, height: 6)
+                            .shadow(color: Color.exoYellow.opacity(0.6), radius: 4)
+                        Text("EXO")
+                            .font(.exoMono(10, weight: .bold))
+                            .tracking(1.5)
+                            .foregroundStyle(Color.exoYellow)
+                    } else {
+                        Text("QUERY")
+                            .font(.exoMono(10, weight: .medium))
+                            .tracking(1.5)
+                            .foregroundStyle(Color.exoLightGray)
+                    }
+                }
+
+                // Bubble
+                HStack(spacing: 0) {
+                    if isAssistant {
+                        RoundedRectangle(cornerRadius: 1)
+                            .fill(Color.exoYellow.opacity(0.5))
+                            .frame(width: 2)
+                    }
+
+                    Text(message.content + (message.isStreaming ? " \u{258C}" : ""))
+                        .font(.exoBody)
+                        .textSelection(.enabled)
+                        .foregroundStyle(Color.exoForeground)
+                        .padding(.horizontal, 14)
+                        .padding(.vertical, 10)
+                }
+                .background(Color.exoDarkGray)
+                .clipShape(RoundedRectangle(cornerRadius: 8))
+            }
+
+            if isAssistant { Spacer(minLength: 48) }
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/Chat/ModelSelectorView.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/Chat/ModelSelectorView.swift
@@ -0,0 +1,75 @@
+import SwiftUI
+
+struct ModelSelectorView: View {
+    let models: [ModelOption]
+    let selectedModelId: String?
+    let onSelect: (String) -> Void
+    @Environment(\.dismiss) private var dismiss
+
+    var body: some View {
+        NavigationStack {
+            List {
+                if models.isEmpty {
+                    emptyContent
+                } else {
+                    modelsList
+                }
+            }
+            .scrollContentBackground(.hidden)
+            .background(Color.exoBlack)
+            .navigationTitle("SELECT MODEL")
+            .navigationBarTitleDisplayMode(.inline)
+            .toolbar {
+                ToolbarItem(placement: .cancellationAction) {
+                    Button("Cancel") { dismiss() }
+                        .font(.exoSubheadline)
+                        .foregroundStyle(Color.exoYellow)
+                }
+            }
+        }
+    }
+
+    private var emptyContent: some View {
+        ContentUnavailableView(
+            "No Models Available",
+            systemImage: "cpu",
+            description: Text("Connect to an EXO cluster to see available models.")
+        )
+        .foregroundStyle(Color.exoLightGray)
+        .listRowBackground(Color.exoBlack)
+    }
+
+    private var modelsList: some View {
+        ForEach(models) { model in
+            Button {
+                onSelect(model.id)
+                dismiss()
+            } label: {
+                modelRow(model)
+            }
+            .tint(.primary)
+            .listRowBackground(Color.exoDarkGray)
+        }
+    }
+
+    private func modelRow(_ model: ModelOption) -> some View {
+        HStack {
+            VStack(alignment: .leading, spacing: 2) {
+                Text(model.displayName)
+                    .font(.exoSubheadline)
+                    .foregroundStyle(Color.exoForeground)
+                Text(model.id)
+                    .font(.exoCaption)
+                    .foregroundStyle(Color.exoLightGray)
+            }
+
+            Spacer()
+
+            if model.id == selectedModelId {
+                Image(systemName: "checkmark")
+                    .font(.exoSubheadline)
+                    .foregroundStyle(Color.exoYellow)
+            }
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/Components/ConnectionStatusBadge.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/Components/ConnectionStatusBadge.swift
@@ -0,0 +1,68 @@
+import SwiftUI
+
+struct ConnectionStatusBadge: View {
+    let connectionState: ConnectionState
+    var localModelState: LocalModelState = .notDownloaded
+
+    private var isLocalReady: Bool {
+        if case .disconnected = connectionState {
+            return localModelState == .ready || localModelState == .generating
+        }
+        return false
+    }
+
+    var body: some View {
+        HStack(spacing: 6) {
+            Circle()
+                .fill(dotColor)
+                .frame(width: 8, height: 8)
+                .shadow(color: dotColor.opacity(0.6), radius: 4)
+
+            Text(label.uppercased())
+                .font(.exoMono(10, weight: .medium))
+                .tracking(1)
+                .foregroundStyle(Color.exoForeground)
+        }
+        .padding(.horizontal, 10)
+        .padding(.vertical, 5)
+        .background(backgroundColor)
+        .clipShape(Capsule())
+        .overlay(
+            Capsule()
+                .stroke(dotColor.opacity(0.3), lineWidth: 1)
+        )
+    }
+
+    private var dotColor: Color {
+        if isLocalReady {
+            return .exoYellow
+        }
+        switch connectionState {
+        case .connected: return .green
+        case .connecting: return .orange
+        case .disconnected: return .exoLightGray
+        }
+    }
+
+    private var label: String {
+        if isLocalReady {
+            return "Local"
+        }
+        switch connectionState {
+        case .connected: return "Connected"
+        case .connecting: return "Connecting"
+        case .disconnected: return "Disconnected"
+        }
+    }
+
+    private var backgroundColor: Color {
+        if isLocalReady {
+            return Color.exoYellow.opacity(0.1)
+        }
+        switch connectionState {
+        case .connected: return .green.opacity(0.1)
+        case .connecting: return .orange.opacity(0.1)
+        case .disconnected: return Color.exoMediumGray.opacity(0.5)
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/RootView.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/RootView.swift
@@ -0,0 +1,136 @@
+import SwiftUI
+
+struct RootView: View {
+    @Environment(ClusterService.self) private var clusterService
+    @Environment(DiscoveryService.self) private var discoveryService
+    @Environment(ChatService.self) private var chatService
+    @Environment(LocalInferenceService.self) private var localInferenceService
+    @State private var showSettings = false
+    @State private var showConversations = false
+
+    var body: some View {
+        NavigationStack {
+            ChatView()
+                .navigationTitle("EXO")
+                .navigationBarTitleDisplayMode(.inline)
+                .toolbar {
+                    ToolbarItem(placement: .topBarLeading) {
+                        conversationMenuButton
+                    }
+
+                    ToolbarItem(placement: .principal) {
+                        ConnectionStatusBadge(
+                            connectionState: clusterService.connectionState,
+                            localModelState: localInferenceService.modelState
+                        )
+                    }
+
+                    ToolbarItem(placement: .topBarTrailing) {
+                        Button {
+                            showSettings = true
+                        } label: {
+                            Image(systemName: "gear")
+                                .foregroundStyle(Color.exoYellow)
+                        }
+                    }
+                }
+        }
+        .tint(Color.exoYellow)
+        .sheet(isPresented: $showSettings) {
+            SettingsView()
+                .environment(discoveryService)
+                .presentationBackground(Color.exoDarkGray)
+        }
+        .sheet(isPresented: $showConversations) {
+            conversationList
+                .presentationBackground(Color.exoDarkGray)
+        }
+    }
+
+    // MARK: - Conversations
+
+    private var conversationMenuButton: some View {
+        HStack(spacing: 12) {
+            Button {
+                showConversations = true
+            } label: {
+                Image(systemName: "sidebar.left")
+                    .foregroundStyle(Color.exoYellow)
+            }
+
+            Button {
+                chatService.createConversation()
+            } label: {
+                Image(systemName: "square.and.pencil")
+                    .foregroundStyle(Color.exoYellow)
+            }
+        }
+    }
+
+    private var conversationList: some View {
+        NavigationStack {
+            List {
+                if chatService.conversations.isEmpty {
+                    Text("No conversations yet")
+                        .font(.exoBody)
+                        .foregroundStyle(Color.exoLightGray)
+                        .listRowBackground(Color.exoDarkGray)
+                } else {
+                    ForEach(chatService.conversations) { conversation in
+                        let isActive = conversation.id == chatService.activeConversationId
+                        Button {
+                            chatService.setActiveConversation(id: conversation.id)
+                            showConversations = false
+                        } label: {
+                            VStack(alignment: .leading, spacing: 4) {
+                                Text(conversation.title)
+                                    .font(.exoSubheadline)
+                                    .fontWeight(isActive ? .semibold : .regular)
+                                    .foregroundStyle(
+                                        isActive ? Color.exoYellow : Color.exoForeground
+                                    )
+                                    .lineLimit(1)
+
+                                if let modelId = conversation.modelId {
+                                    Text(modelId)
+                                        .font(.exoCaption)
+                                        .foregroundStyle(Color.exoLightGray)
+                                        .lineLimit(1)
+                                }
+                            }
+                        }
+                        .listRowBackground(
+                            isActive
+                                ? Color.exoYellow.opacity(0.1)
+                                : Color.exoDarkGray
+                        )
+                    }
+                    .onDelete { indexSet in
+                        for index in indexSet {
+                            chatService.deleteConversation(id: chatService.conversations[index].id)
+                        }
+                    }
+                }
+            }
+            .scrollContentBackground(.hidden)
+            .background(Color.exoBlack)
+            .navigationTitle("Conversations")
+            .navigationBarTitleDisplayMode(.inline)
+            .toolbar {
+                ToolbarItem(placement: .confirmationAction) {
+                    Button("Done") { showConversations = false }
+                        .font(.exoSubheadline)
+                        .foregroundStyle(Color.exoYellow)
+                }
+                ToolbarItem(placement: .topBarLeading) {
+                    Button {
+                        chatService.createConversation()
+                    } label: {
+                        Image(systemName: "plus")
+                            .foregroundStyle(Color.exoYellow)
+                    }
+                }
+            }
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/Settings/SettingsView.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/Settings/SettingsView.swift
@@ -0,0 +1,314 @@
+import SwiftUI
+
+struct SettingsView: View {
+    @Environment(ClusterService.self) private var clusterService
+    @Environment(DiscoveryService.self) private var discoveryService
+    @Environment(LocalInferenceService.self) private var localInferenceService
+    @Environment(\.dismiss) private var dismiss
+    @State private var host: String = ""
+    @State private var port: String = "52415"
+
+    var body: some View {
+        NavigationStack {
+            Form {
+                localModelSection
+                nearbyClustersSection
+                connectionSection
+                statusSection
+            }
+            .scrollContentBackground(.hidden)
+            .background(Color.exoBlack)
+            .navigationTitle("Settings")
+            .navigationBarTitleDisplayMode(.inline)
+            .toolbar {
+                ToolbarItem(placement: .confirmationAction) {
+                    Button("Done") { dismiss() }
+                        .font(.exoSubheadline)
+                        .foregroundStyle(Color.exoYellow)
+                }
+            }
+        }
+    }
+
+    // MARK: - Section Headers
+
+    private func sectionHeader(_ title: String) -> some View {
+        Text(title.uppercased())
+            .font(.exoMono(10, weight: .semibold))
+            .tracking(2)
+            .foregroundStyle(Color.exoYellow)
+    }
+
+    // MARK: - Local Model
+
+    private var localModelSection: some View {
+        Section {
+            HStack {
+                VStack(alignment: .leading, spacing: 4) {
+                    Text(localInferenceService.defaultModelId)
+                        .font(.exoSubheadline)
+                        .foregroundStyle(Color.exoForeground)
+
+                    Text(localModelStatusText)
+                        .font(.exoCaption)
+                        .foregroundStyle(Color.exoLightGray)
+                }
+
+                Spacer()
+
+                localModelActionButton
+            }
+            .listRowBackground(Color.exoDarkGray)
+
+            if case .downloading(let progress) = localInferenceService.modelState {
+                ProgressView(value: progress)
+                    .tint(Color.exoYellow)
+                    .listRowBackground(Color.exoDarkGray)
+            }
+        } header: {
+            sectionHeader("Local Model")
+        } footer: {
+            Text(
+                "When disconnected from a cluster, messages are processed on-device using this model."
+            )
+            .font(.exoCaption)
+            .foregroundStyle(Color.exoLightGray.opacity(0.7))
+        }
+    }
+
+    private var localModelStatusText: String {
+        switch localInferenceService.modelState {
+        case .notDownloaded: "Not downloaded"
+        case .downloading(let progress): "Downloading \(Int(progress * 100))%..."
+        case .downloaded: "Downloaded — not loaded"
+        case .loading: "Loading into memory..."
+        case .ready: "Ready"
+        case .generating: "Generating..."
+        case .error(let message): "Error: \(message)"
+        }
+    }
+
+    @ViewBuilder
+    private var localModelActionButton: some View {
+        switch localInferenceService.modelState {
+        case .notDownloaded:
+            exoButton("Download") {
+                Task { await localInferenceService.prepareModel() }
+            }
+        case .downloading:
+            ProgressView()
+                .controlSize(.small)
+                .tint(Color.exoYellow)
+        case .downloaded:
+            exoButton("Load") {
+                Task { await localInferenceService.prepareModel() }
+            }
+        case .loading:
+            ProgressView()
+                .controlSize(.small)
+                .tint(Color.exoYellow)
+        case .ready, .generating:
+            exoButton("Unload") {
+                localInferenceService.unloadModel()
+            }
+        case .error:
+            exoButton("Retry", destructive: true) {
+                Task { await localInferenceService.prepareModel() }
+            }
+        }
+    }
+
+    private func exoButton(_ title: String, destructive: Bool = false, action: @escaping () -> Void)
+        -> some View
+    {
+        let borderColor = destructive ? Color.exoDestructive : Color.exoYellow
+        return Button(action: action) {
+            Text(title.uppercased())
+                .font(.exoMono(11, weight: .semibold))
+                .tracking(1)
+                .foregroundStyle(borderColor)
+                .padding(.horizontal, 10)
+                .padding(.vertical, 5)
+                .overlay(
+                    RoundedRectangle(cornerRadius: 6)
+                        .stroke(borderColor, lineWidth: 1)
+                )
+        }
+    }
+
+    // MARK: - Nearby Clusters
+
+    private var nearbyClustersSection: some View {
+        Section {
+            if discoveryService.discoveredClusters.isEmpty {
+                if discoveryService.isSearching {
+                    HStack {
+                        ProgressView()
+                            .tint(Color.exoYellow)
+                            .padding(.trailing, 8)
+                        Text("Searching for clusters...")
+                            .font(.exoBody)
+                            .foregroundStyle(Color.exoLightGray)
+                    }
+                    .listRowBackground(Color.exoDarkGray)
+                } else {
+                    Text("No clusters found")
+                        .font(.exoBody)
+                        .foregroundStyle(Color.exoLightGray)
+                        .listRowBackground(Color.exoDarkGray)
+                }
+            } else {
+                ForEach(discoveryService.discoveredClusters) { cluster in
+                    HStack {
+                        VStack(alignment: .leading) {
+                            Text(cluster.name)
+                                .font(.exoBody)
+                                .foregroundStyle(Color.exoForeground)
+                        }
+                        Spacer()
+                        exoButton("Connect") {
+                            Task {
+                                await clusterService.connectToDiscoveredCluster(
+                                    cluster, using: discoveryService
+                                )
+                                if clusterService.isConnected {
+                                    dismiss()
+                                }
+                            }
+                        }
+                    }
+                    .listRowBackground(Color.exoDarkGray)
+                }
+            }
+        } header: {
+            sectionHeader("Nearby Clusters")
+        }
+    }
+
+    // MARK: - Manual Connection
+
+    private var connectionSection: some View {
+        Section {
+            TextField("IP Address (e.g. 192.168.1.42)", text: $host)
+                .font(.exoBody)
+                .keyboardType(.decimalPad)
+                .textContentType(.URL)
+                .autocorrectionDisabled()
+                .foregroundStyle(Color.exoForeground)
+                .listRowBackground(Color.exoDarkGray)
+
+            TextField("Port", text: $port)
+                .font(.exoBody)
+                .keyboardType(.numberPad)
+                .foregroundStyle(Color.exoForeground)
+                .listRowBackground(Color.exoDarkGray)
+
+            Button {
+                Task {
+                    let portNum = Int(port) ?? ConnectionInfo.defaultPort
+                    let info = ConnectionInfo(host: host, port: portNum, nodeId: nil)
+                    await clusterService.connect(to: info)
+                    if clusterService.isConnected {
+                        dismiss()
+                    }
+                }
+            } label: {
+                Text(clusterService.isConnected ? "RECONNECT" : "CONNECT")
+                    .font(.exoMono(13, weight: .semibold))
+                    .tracking(1.5)
+                    .foregroundStyle(
+                        host.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
+                            ? Color.exoLightGray : Color.exoYellow
+                    )
+                    .frame(maxWidth: .infinity)
+            }
+            .disabled(host.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty)
+            .listRowBackground(Color.exoDarkGray)
+        } header: {
+            sectionHeader("Manual Connection")
+        }
+    }
+
+    // MARK: - Status
+
+    private var statusSection: some View {
+        Section {
+            if let connection = clusterService.currentConnection {
+                LabeledContent {
+                    Text(connection.host)
+                        .font(.exoCaption)
+                        .foregroundStyle(Color.exoForeground)
+                } label: {
+                    Text("Host")
+                        .font(.exoCaption)
+                        .foregroundStyle(Color.exoLightGray)
+                }
+                .listRowBackground(Color.exoDarkGray)
+
+                LabeledContent {
+                    Text("\(connection.port)")
+                        .font(.exoCaption)
+                        .foregroundStyle(Color.exoForeground)
+                } label: {
+                    Text("Port")
+                        .font(.exoCaption)
+                        .foregroundStyle(Color.exoLightGray)
+                }
+                .listRowBackground(Color.exoDarkGray)
+
+                if let nodeId = connection.nodeId {
+                    LabeledContent {
+                        Text(String(nodeId.prefix(12)) + "...")
+                            .font(.exoCaption)
+                            .foregroundStyle(Color.exoForeground)
+                    } label: {
+                        Text("Node ID")
+                            .font(.exoCaption)
+                            .foregroundStyle(Color.exoLightGray)
+                    }
+                    .listRowBackground(Color.exoDarkGray)
+                }
+
+                LabeledContent {
+                    Text("\(clusterService.availableModels.count)")
+                        .font(.exoCaption)
+                        .foregroundStyle(Color.exoForeground)
+                } label: {
+                    Text("Models")
+                        .font(.exoCaption)
+                        .foregroundStyle(Color.exoLightGray)
+                }
+                .listRowBackground(Color.exoDarkGray)
+
+                Button(role: .destructive) {
+                    clusterService.disconnect()
+                } label: {
+                    Text("DISCONNECT")
+                        .font(.exoMono(13, weight: .semibold))
+                        .tracking(1.5)
+                        .foregroundStyle(Color.exoDestructive)
+                        .frame(maxWidth: .infinity)
+                }
+                .listRowBackground(Color.exoDarkGray)
+            } else {
+                if let error = clusterService.lastError {
+                    Label {
+                        Text(error)
+                            .font(.exoCaption)
+                    } icon: {
+                        Image(systemName: "exclamationmark.triangle")
+                    }
+                    .foregroundStyle(Color.exoDestructive)
+                    .listRowBackground(Color.exoDarkGray)
+                } else {
+                    Text("Not connected")
+                        .font(.exoBody)
+                        .foregroundStyle(Color.exoLightGray)
+                        .listRowBackground(Color.exoDarkGray)
+                }
+            }
+        } header: {
+            sectionHeader("Status")
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/Theme/EXOTheme.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/Theme/EXOTheme.swift
@@ -0,0 +1,51 @@
+import SwiftUI
+
+// MARK: - EXO Color Palette
+
+extension Color {
+    /// Primary background — near-black (#121212)
+    static let exoBlack = Color(red: 0x12 / 255.0, green: 0x12 / 255.0, blue: 0x12 / 255.0)
+    /// Card / surface background (#1F1F1F)
+    static let exoDarkGray = Color(red: 0x1F / 255.0, green: 0x1F / 255.0, blue: 0x1F / 255.0)
+    /// Input field / elevated surface (#353535)
+    static let exoMediumGray = Color(red: 0x35 / 255.0, green: 0x35 / 255.0, blue: 0x35 / 255.0)
+    /// Secondary text (#999999)
+    static let exoLightGray = Color(red: 0x99 / 255.0, green: 0x99 / 255.0, blue: 0x99 / 255.0)
+    /// Accent yellow — matches dashboard (#FFD700)
+    static let exoYellow = Color(red: 0xFF / 255.0, green: 0xD7 / 255.0, blue: 0x00 / 255.0)
+    /// Primary foreground text (#E5E5E5)
+    static let exoForeground = Color(red: 0xE5 / 255.0, green: 0xE5 / 255.0, blue: 0xE5 / 255.0)
+    /// Destructive / error (#E74C3C)
+    static let exoDestructive = Color(red: 0xE7 / 255.0, green: 0x4C / 255.0, blue: 0x3C / 255.0)
+}
+
+// MARK: - EXO Typography (SF Mono via .monospaced design)
+
+extension Font {
+    /// Monospaced font at a given size and weight.
+    static func exoMono(_ size: CGFloat, weight: Font.Weight = .regular) -> Font {
+        .system(size: size, weight: weight, design: .monospaced)
+    }
+
+    /// Body text — 15pt monospaced
+    static let exoBody: Font = .system(size: 15, weight: .regular, design: .monospaced)
+    /// Caption — 11pt monospaced
+    static let exoCaption: Font = .system(size: 11, weight: .regular, design: .monospaced)
+    /// Subheadline — 13pt monospaced medium
+    static let exoSubheadline: Font = .system(size: 13, weight: .medium, design: .monospaced)
+    /// Headline — 17pt monospaced semibold
+    static let exoHeadline: Font = .system(size: 17, weight: .semibold, design: .monospaced)
+}
+
+// MARK: - Reusable Gradient Divider
+
+struct GradientDivider: View {
+    var body: some View {
+        LinearGradient(
+            colors: [.clear, Color.exoYellow.opacity(0.3), .clear],
+            startPoint: .leading,
+            endPoint: .trailing
+        )
+        .frame(height: 1)
+    }
+}
--- a/app/EXO-iOS/EXO-iOSTests/EXO_iOSTests.swift
+++ b/app/EXO-iOS/EXO-iOSTests/EXO_iOSTests.swift
@@ -0,0 +1,18 @@
+//
+//  EXO_iOSTests.swift
+//  EXO-iOSTests
+//
+//  Created by Sami Khan on 2026-02-17.
+//
+
+import Testing
+
+@testable import EXO_iOS
+
+struct EXO_iOSTests {
+
+    @Test func example() async throws {
+        // Write your test here and use APIs like `#expect(...)` to check expected conditions.
+    }
+
+}
--- a/app/EXO-iOS/EXO-iOSUITests/EXO_iOSUITests.swift
+++ b/app/EXO-iOS/EXO-iOSUITests/EXO_iOSUITests.swift
@@ -0,0 +1,41 @@
+//
+//  EXO_iOSUITests.swift
+//  EXO-iOSUITests
+//
+//  Created by Sami Khan on 2026-02-17.
+//
+
+import XCTest
+
+final class EXO_iOSUITests: XCTestCase {
+
+    override func setUpWithError() throws {
+        // Put setup code here. This method is called before the invocation of each test method in the class.
+
+        // In UI tests it is usually best to stop immediately when a failure occurs.
+        continueAfterFailure = false
+
+        // In UI tests it’s important to set the initial state - such as interface orientation - required for your tests before they run. The setUp method is a good place to do this.
+    }
+
+    override func tearDownWithError() throws {
+        // Put teardown code here. This method is called after the invocation of each test method in the class.
+    }
+
+    @MainActor
+    func testExample() throws {
+        // UI tests must launch the application that they test.
+        let app = XCUIApplication()
+        app.launch()
+
+        // Use XCTAssert and related functions to verify your tests produce the correct results.
+    }
+
+    @MainActor
+    func testLaunchPerformance() throws {
+        // This measures how long it takes to launch your application.
+        measure(metrics: [XCTApplicationLaunchMetric()]) {
+            XCUIApplication().launch()
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOSUITests/EXO_iOSUITestsLaunchTests.swift
+++ b/app/EXO-iOS/EXO-iOSUITests/EXO_iOSUITestsLaunchTests.swift
@@ -0,0 +1,33 @@
+//
+//  EXO_iOSUITestsLaunchTests.swift
+//  EXO-iOSUITests
+//
+//  Created by Sami Khan on 2026-02-17.
+//
+
+import XCTest
+
+final class EXO_iOSUITestsLaunchTests: XCTestCase {
+
+    override class var runsForEachTargetApplicationUIConfiguration: Bool {
+        true
+    }
+
+    override func setUpWithError() throws {
+        continueAfterFailure = false
+    }
+
+    @MainActor
+    func testLaunch() throws {
+        let app = XCUIApplication()
+        app.launch()
+
+        // Insert steps here to perform after app launch but before taking a screenshot,
+        // such as logging into a test account or navigating somewhere in the app
+
+        let attachment = XCTAttachment(screenshot: app.screenshot())
+        attachment.name = "Launch Screen"
+        attachment.lifetime = .keepAlways
+        add(attachment)
+    }
+}
--- a/app/EXO/EXO/ExoProcessController.swift
+++ b/app/EXO/EXO/ExoProcessController.swift
@@ -126,37 +126,11 @@ final class ExoProcessController: ObservableObject {
            return
        }
        process.terminationHandler = nil
-        status = .stopped
-
-        guard process.isRunning else {
-            self.process = nil
-            return
+        if process.isRunning {
+            process.terminate()
        }
-
-        let proc = process
        self.process = nil
-
-        Task.detached {
-            proc.interrupt()
-
-            for _ in 0..<50 {
-                if !proc.isRunning { return }
-                try? await Task.sleep(nanoseconds: 100_000_000)
-            }
-
-            if proc.isRunning {
-                proc.terminate()
-            }
-
-            for _ in 0..<30 {
-                if !proc.isRunning { return }
-                try? await Task.sleep(nanoseconds: 100_000_000)
-            }
-
-            if proc.isRunning {
-                kill(proc.processIdentifier, SIGKILL)
-            }
-        }
+        status = .stopped
    }

    func restart() {
--- a/dashboard/src/app.css
+++ b/dashboard/src/app.css
@@ -16,10 +16,9 @@
 	/* Gotham-inspired accent colors */
 	--exo-grid: oklch(0.25 0 0);
 	--exo-scanline: oklch(0.15 0 0);
-	--exo-glow-yellow: oklch(0.85 0.18 85 / 0.3);
-	--exo-glow-yellow-strong: oklch(0.85 0.18 85 / 0.5);
-	--exo-bg-hover: oklch(0.18 0 0);
-
+	--exo-glow-yellow: 0 0 20px oklch(0.85 0.18 85 / 0.3);
+	--exo-glow-yellow-strong: 0 0 40px oklch(0.85 0.18 85 / 0.5);
+	
 	/* Theme Variables */
 	--radius: 0.375rem;
 	--background: var(--exo-black);
@@ -42,237 +41,6 @@
 	--ring: var(--exo-yellow);
 }

-/* ============================================================
-   LIGHT THEME — "Mission Control, Dawn Shift"
-   Warm parchment + deep amber. Applied when <html> has .light class.
-   ============================================================ */
-html.light {
-	/* EXO brand palette — warm amber shift */
-	--exo-black: oklch(0.97 0.015 80);
-	--exo-dark-gray: oklch(0.92 0.012 80);
-	--exo-medium-gray: oklch(0.83 0.009 78);
-	--exo-light-gray: oklch(0.50 0.018 75);
-	--exo-yellow: oklch(0.50 0.14 65);
-	--exo-yellow-darker: oklch(0.40 0.13 65);
-	--exo-yellow-glow: oklch(0.60 0.14 65);
-
-	--exo-grid: oklch(0.88 0.009 80);
-	--exo-scanline: oklch(0.93 0.010 80);
-	--exo-glow-yellow: oklch(0.50 0.14 65 / 0.12);
-	--exo-glow-yellow-strong: oklch(0.50 0.14 65 / 0.22);
-	--exo-bg-hover: oklch(0.89 0.010 80);
-
-	/* Semantic tokens */
-	--background: oklch(0.97 0.015 80);
-	--foreground: oklch(0.13 0.015 75);
-	--card: oklch(0.92 0.012 80);
-	--card-foreground: oklch(0.13 0.015 75);
-	--popover: oklch(0.95 0.012 80);
-	--popover-foreground: oklch(0.13 0.015 75);
-	--primary: oklch(0.50 0.14 65);
-	--primary-foreground: oklch(0.97 0.015 80);
-	--secondary: oklch(0.88 0.008 80);
-	--secondary-foreground: oklch(0.15 0.012 75);
-	--muted: oklch(0.90 0.009 80);
-	--muted-foreground: oklch(0.50 0.018 75);
-	--accent: oklch(0.88 0.008 80);
-	--accent-foreground: oklch(0.15 0.012 75);
-	--destructive: oklch(0.52 0.22 25);
-	--border: oklch(0.84 0.007 78);
-	--input: oklch(0.87 0.008 80);
-	--ring: oklch(0.50 0.14 65);
-}
-
-/* ============================================================
-   LIGHT MODE UTILITY OVERRIDES
-   ============================================================ */
-html.light {
-	& .text-white,
-	& .text-white\/90,
-	& .text-white\/80,
-	& .text-white\/70 {
-		color: var(--foreground) !important;
-	}
-	& .text-white\/60,
-	& .text-white\/50 {
-		color: color-mix(in oklch, var(--foreground) 60%, transparent) !important;
-	}
-	& .text-white\/40,
-	& .text-white\/30 {
-		color: color-mix(in oklch, var(--foreground) 38%, transparent) !important;
-	}
-
-	& .bg-black\/80,
-	& .bg-black\/60,
-	& .bg-black\/50,
-	& .bg-black\/40 {
-		background-color: oklch(0.90 0.010 80 / 0.7) !important;
-	}
-	& [class*="bg-exo-black/"] {
-		background-color: oklch(0.90 0.010 80 / 0.6) !important;
-	}
-	& [class*="shadow-black"] {
-		--tw-shadow-color: oklch(0.30 0.010 75 / 0.10) !important;
-	}
-
-	& ::-webkit-scrollbar-track {
-		background: oklch(0.93 0.010 80) !important;
-	}
-	& ::-webkit-scrollbar-thumb {
-		background: oklch(0.76 0.010 78) !important;
-	}
-	& ::-webkit-scrollbar-thumb:hover {
-		background: oklch(0.50 0.14 65 / 0.6) !important;
-	}
-
-	& .command-panel {
-		background: linear-gradient(
-			180deg,
-			oklch(0.94 0.012 80 / 0.96) 0%,
-			oklch(0.91 0.010 80 / 0.98) 100%
-		) !important;
-		border-color: oklch(0.82 0.008 78) !important;
-		box-shadow:
-			inset 0 1px 0 oklch(1 0 0 / 0.6),
-			0 4px 20px oklch(0.30 0.010 75 / 0.08) !important;
-	}
-
-	& .glow-text {
-		text-shadow:
-			0 0 12px oklch(0.50 0.14 65 / 0.20),
-			0 1px 3px oklch(0.30 0.010 75 / 0.12) !important;
-	}
-
-	& .grid-bg {
-		background-image:
-			linear-gradient(oklch(0.75 0.008 78 / 0.25) 1px, transparent 1px),
-			linear-gradient(90deg, oklch(0.75 0.008 78 / 0.25) 1px, transparent 1px) !important;
-	}
-
-	& .scanlines::before {
-		background: repeating-linear-gradient(
-			0deg,
-			transparent,
-			transparent 2px,
-			oklch(0.50 0.010 78 / 0.018) 2px,
-			oklch(0.50 0.010 78 / 0.018) 4px
-		) !important;
-	}
-
-	& .crt-screen {
-		background: radial-gradient(
-			ellipse at center,
-			oklch(0.95 0.012 80) 0%,
-			oklch(0.92 0.010 80) 50%,
-			oklch(0.89 0.009 80) 100%
-		) !important;
-		box-shadow:
-			inset 0 0 60px oklch(0.30 0.010 75 / 0.04),
-			0 0 30px oklch(0.50 0.14 65 / 0.04) !important;
-	}
-
-	& .graph-link {
-		stroke: oklch(0.50 0.018 75 / 0.45) !important;
-		filter: none !important;
-	}
-	& .graph-link-active {
-		stroke: oklch(0.50 0.14 65 / 0.75) !important;
-		filter: none !important;
-	}
-
-	& .shooting-stars {
-		display: none !important;
-	}
-
-	& img[alt="EXO"] {
-		filter: brightness(0) drop-shadow(0 0 6px oklch(0.30 0.010 75 / 0.10)) !important;
-	}
-
-	& .text-red-400 { color: oklch(0.52 0.22 25) !important; }
-	& .text-green-400 { color: oklch(0.48 0.17 155) !important; }
-	& .text-blue-200,
-	& .text-blue-300,
-	& .text-blue-400 { color: oklch(0.48 0.17 250) !important; }
-
-	& .bg-red-500\/10 { background-color: oklch(0.52 0.22 25 / 0.07) !important; }
-	& .bg-red-500\/20 { background-color: oklch(0.52 0.22 25 / 0.11) !important; }
-	& .bg-red-500\/30 { background-color: oklch(0.52 0.22 25 / 0.14) !important; }
-
-	& textarea,
-	& input[type="text"] { color: var(--foreground) !important; }
-	& textarea::placeholder,
-	& input::placeholder { color: oklch(0.50 0.012 78 / 0.55) !important; }
-
-	& .code-block-wrapper,
-	& .math-display-wrapper {
-		background: oklch(0.95 0.010 80) !important;
-		border-color: oklch(0.83 0.007 78) !important;
-	}
-	& .code-block-header,
-	& .math-display-header {
-		background: oklch(0.91 0.009 80) !important;
-		border-color: oklch(0.85 0.007 78) !important;
-	}
-	& .inline-code {
-		background: oklch(0.89 0.009 80) !important;
-		color: oklch(0.20 0.012 75) !important;
-	}
-
-	& blockquote { background: oklch(0.93 0.010 80) !important; }
-	& th {
-		background: oklch(0.90 0.009 80) !important;
-		border-color: oklch(0.80 0.007 78) !important;
-	}
-	& td { border-color: oklch(0.84 0.007 78) !important; }
-	& hr { border-color: oklch(0.84 0.007 78) !important; }
-
-	& .hljs { color: oklch(0.22 0.012 75) !important; }
-	& .hljs-keyword, & .hljs-selector-tag, & .hljs-literal, & .hljs-section, & .hljs-link {
-		color: oklch(0.45 0.18 300) !important;
-	}
-	& .hljs-string, & .hljs-title, & .hljs-name, & .hljs-type,
-	& .hljs-attribute, & .hljs-symbol, & .hljs-bullet, & .hljs-addition,
-	& .hljs-variable, & .hljs-template-tag, & .hljs-template-variable {
-		color: oklch(0.45 0.14 65) !important;
-	}
-	& .hljs-comment, & .hljs-quote, & .hljs-deletion, & .hljs-meta {
-		color: oklch(0.55 0.010 78) !important;
-	}
-	& .hljs-number, & .hljs-regexp, & .hljs-built_in {
-		color: oklch(0.45 0.15 160) !important;
-	}
-	& .hljs-function, & .hljs-class .hljs-title {
-		color: oklch(0.42 0.17 240) !important;
-	}
-
-	& .katex, & .katex .mord, & .katex .minner, & .katex .mop,
-	& .katex .mbin, & .katex .mrel, & .katex .mpunct {
-		color: oklch(0.15 0.012 75) !important;
-	}
-	& .katex .frac-line, & .katex .overline-line, & .katex .underline-line,
-	& .katex .hline, & .katex .rule {
-		border-color: oklch(0.25 0.012 75) !important;
-		background: oklch(0.25 0.012 75) !important;
-	}
-	& .katex svg { fill: oklch(0.25 0.012 75) !important; stroke: oklch(0.25 0.012 75) !important; }
-	& .katex svg path { stroke: oklch(0.25 0.012 75) !important; }
-	& .katex .mopen, & .katex .mclose,
-	& .katex .delimsizing, & [class^="katex .delim-size"] {
-		color: oklch(0.35 0.012 75) !important;
-	}
-
-	& .latex-proof { background: oklch(0.96 0.010 80) !important; border-left-color: oklch(0.72 0.010 78) !important; }
-	& .latex-proof-header { color: oklch(0.22 0.012 75) !important; }
-	& .latex-proof-content { color: oklch(0.15 0.012 75) !important; }
-	& .latex-proof-content::after { color: oklch(0.48 0.012 75) !important; }
-	& .latex-theorem { background: oklch(0.94 0.010 80) !important; border-color: oklch(0.80 0.008 78) !important; }
-	& .latex-diagram-placeholder {
-		background: oklch(0.96 0.010 80) !important;
-		border-color: oklch(0.80 0.008 78) !important;
-		color: oklch(0.38 0.012 75) !important;
-	}
-}
-
@theme inline {
 	--radius-sm: calc(var(--radius) - 2px);
 	--radius-md: var(--radius);
--- a/dashboard/src/app.html
+++ b/dashboard/src/app.html
@@ -1,15 +1,7 @@
 <!doctype html>
-<html lang="en" class="dark">
+<html lang="en">
 	<head>
 		<meta charset="utf-8" />
-		<script>
-			try {
-				if (localStorage.getItem('exo-theme') === 'light') {
-					document.documentElement.classList.remove('dark');
-					document.documentElement.classList.add('light');
-				}
-			} catch (_) {}
-		</script>
 		<link rel="icon" href="%sveltekit.assets%/favicon.ico" />
 		<meta name="viewport" content="width=device-width, initial-scale=1" />
 		<title>EXO</title>
--- a/dashboard/src/lib/components/ChatForm.svelte
+++ b/dashboard/src/lib/components/ChatForm.svelte
@@ -103,7 +103,7 @@
  const modelSupportsThinking = $derived(() => {
    if (!currentModel) return false;
    const caps = modelCapabilities[currentModel] || [];
-    return caps.includes("thinking_toggle") && caps.includes("text");
+    return caps.includes("thinking") && caps.includes("text");
  });

  const isEditOnlyWithoutImage = $derived(
--- a/dashboard/src/lib/components/HeaderNav.svelte
+++ b/dashboard/src/lib/components/HeaderNav.svelte
@@ -1,6 +1,5 @@
 <script lang="ts">
  import { browser } from "$app/environment";
-  import { theme } from "$lib/stores/theme.svelte";

  export let showHome = true;
  export let onHome: (() => void) | null = null;
@@ -80,48 +79,10 @@
    />
  </button>

-  <!-- Right: Theme toggle + Home + Downloads -->
+  <!-- Right: Home + Downloads -->
  <div
    class="absolute right-6 top-1/2 -translate-y-1/2 flex items-center gap-4"
  >
-    <button
-      onclick={() => theme.toggle()}
-      class="p-2 rounded border border-exo-medium-gray/40 hover:border-exo-yellow/50 transition-colors cursor-pointer"
-      title={theme.isLight ? "Switch to dark mode" : "Switch to light mode"}
-      aria-label={theme.isLight
-        ? "Switch to dark mode"
-        : "Switch to light mode"}
-    >
-      {#if theme.isLight}
-        <svg
-          class="w-4 h-4 text-exo-light-gray"
-          fill="none"
-          viewBox="0 0 24 24"
-          stroke="currentColor"
-          stroke-width="2"
-        >
-          <path
-            stroke-linecap="round"
-            stroke-linejoin="round"
-            d="M21 12.79A9 9 0 1111.21 3a7 7 0 009.79 9.79z"
-          />
-        </svg>
-      {:else}
-        <svg
-          class="w-4 h-4 text-exo-light-gray"
-          fill="none"
-          viewBox="0 0 24 24"
-          stroke="currentColor"
-          stroke-width="2"
-        >
-          <circle cx="12" cy="12" r="5" />
-          <path
-            stroke-linecap="round"
-            d="M12 1v2m0 18v2M4.22 4.22l1.42 1.42m12.72 12.72l1.42 1.42M1 12h2m18 0h2M4.22 19.78l1.42-1.42M18.36 5.64l1.42-1.42"
-          />
-        </svg>
-      {/if}
-    </button>
    {#if showHome}
      <button
        onclick={handleHome}
--- a/dashboard/src/lib/components/ImageParamsPanel.svelte
+++ b/dashboard/src/lib/components/ImageParamsPanel.svelte
@@ -59,14 +59,13 @@
  }

  const sizeOptions: ImageGenerationParams["size"][] = [
-    "auto",
    "512x512",
    "768x768",
    "1024x1024",
    "1024x768",
    "768x1024",
-    "1024x1536",
-    "1536x1024",
+    "1024x1365",
+    "1365x1024",
  ];

  const qualityOptions: ImageGenerationParams["quality"][] = [
@@ -177,90 +176,92 @@
 <div class="border-b border-exo-medium-gray/30 px-3 py-2">
  <!-- Basic params row -->
  <div class="flex items-center gap-3 flex-wrap">
-    <!-- Size -->
-    <div class="flex items-center gap-1.5">
-      <span class="text-xs text-exo-light-gray uppercase tracking-wider"
-        >SIZE:</span
-      >
-      <div class="relative">
-        <button
-          bind:this={sizeButtonRef}
-          type="button"
-          onclick={() => (isSizeDropdownOpen = !isSizeDropdownOpen)}
-          class="bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-2 pr-6 py-1 text-xs font-mono text-exo-yellow cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70 {isSizeDropdownOpen
-            ? 'border-exo-yellow/70'
-            : ''}"
+    <!-- Size (hidden in edit mode - output size comes from input image) -->
+    {#if !isEditMode}
+      <div class="flex items-center gap-1.5">
+        <span class="text-xs text-exo-light-gray uppercase tracking-wider"
+          >SIZE:</span
        >
-          {params.size.toUpperCase()}
-        </button>
-        <div
-          class="absolute right-1.5 top-1/2 -translate-y-1/2 pointer-events-none transition-transform duration-200 {isSizeDropdownOpen
-            ? 'rotate-180'
-            : ''}"
-        >
-          <svg
-            class="w-3 h-3 text-exo-yellow/60"
-            fill="none"
-            viewBox="0 0 24 24"
-            stroke="currentColor"
+        <div class="relative">
+          <button
+            bind:this={sizeButtonRef}
+            type="button"
+            onclick={() => (isSizeDropdownOpen = !isSizeDropdownOpen)}
+            class="bg-exo-medium-gray/50 border border-exo-yellow/30 rounded pl-2 pr-6 py-1 text-xs font-mono text-exo-yellow cursor-pointer transition-all duration-200 hover:border-exo-yellow/50 focus:outline-none focus:border-exo-yellow/70 {isSizeDropdownOpen
+              ? 'border-exo-yellow/70'
+              : ''}"
          >
-            <path
-              stroke-linecap="round"
-              stroke-linejoin="round"
-              stroke-width="2"
-              d="M19 9l-7 7-7-7"
-            />
-          </svg>
-        </div>
-      </div>
-
-      {#if isSizeDropdownOpen}
-        <!-- Backdrop to close dropdown -->
-        <button
-          type="button"
-          class="fixed inset-0 z-[9998] cursor-default"
-          onclick={() => (isSizeDropdownOpen = false)}
-          aria-label="Close dropdown"
-        ></button>
-
-        <!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
-        <div
-          class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto overflow-x-hidden min-w-max"
-          style="bottom: calc(100vh - {sizeDropdownPosition()
-            .top}px + 4px); left: {sizeDropdownPosition().left}px;"
-        >
-          <div class="py-1">
-            {#each sizeOptions as size}
-              <button
-                type="button"
-                onclick={() => selectSize(size)}
-                class="w-full px-3 py-1.5 text-left text-xs font-mono tracking-wide transition-colors duration-100 flex items-center gap-2 {params.size ===
-                size
-                  ? 'bg-transparent text-exo-yellow'
-                  : 'text-exo-light-gray hover:text-exo-yellow'}"
-              >
-                {#if params.size === size}
-                  <svg
-                    class="w-3 h-3 flex-shrink-0"
-                    fill="currentColor"
-                    viewBox="0 0 20 20"
-                  >
-                    <path
-                      fill-rule="evenodd"
-                      d="M16.707 5.293a1 1 0 010 1.414l-8 8a1 1 0 01-1.414 0l-4-4a1 1 0 011.414-1.414L8 12.586l7.293-7.293a1 1 0 011.414 0z"
-                      clip-rule="evenodd"
-                    />
-                  </svg>
-                {:else}
-                  <span class="w-3"></span>
-                {/if}
-                <span>{size.toUpperCase()}</span>
-              </button>
-            {/each}
+            {params.size}
+          </button>
+          <div
+            class="absolute right-1.5 top-1/2 -translate-y-1/2 pointer-events-none transition-transform duration-200 {isSizeDropdownOpen
+              ? 'rotate-180'
+              : ''}"
+          >
+            <svg
+              class="w-3 h-3 text-exo-yellow/60"
+              fill="none"
+              viewBox="0 0 24 24"
+              stroke="currentColor"
+            >
+              <path
+                stroke-linecap="round"
+                stroke-linejoin="round"
+                stroke-width="2"
+                d="M19 9l-7 7-7-7"
+              />
+            </svg>
          </div>
        </div>
-      {/if}
-    </div>
+
+        {#if isSizeDropdownOpen}
+          <!-- Backdrop to close dropdown -->
+          <button
+            type="button"
+            class="fixed inset-0 z-[9998] cursor-default"
+            onclick={() => (isSizeDropdownOpen = false)}
+            aria-label="Close dropdown"
+          ></button>
+
+          <!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
+          <div
+            class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto min-w-max"
+            style="bottom: calc(100vh - {sizeDropdownPosition()
+              .top}px + 4px); left: {sizeDropdownPosition().left}px;"
+          >
+            <div class="py-1">
+              {#each sizeOptions as size}
+                <button
+                  type="button"
+                  onclick={() => selectSize(size)}
+                  class="w-full px-3 py-1.5 text-left text-xs font-mono tracking-wide transition-colors duration-100 flex items-center gap-2 {params.size ===
+                  size
+                    ? 'bg-transparent text-exo-yellow'
+                    : 'text-exo-light-gray hover:text-exo-yellow'}"
+                >
+                  {#if params.size === size}
+                    <svg
+                      class="w-3 h-3 flex-shrink-0"
+                      fill="currentColor"
+                      viewBox="0 0 20 20"
+                    >
+                      <path
+                        fill-rule="evenodd"
+                        d="M16.707 5.293a1 1 0 010 1.414l-8 8a1 1 0 01-1.414 0l-4-4a1 1 0 011.414-1.414L8 12.586l7.293-7.293a1 1 0 011.414 0z"
+                        clip-rule="evenodd"
+                      />
+                    </svg>
+                  {:else}
+                    <span class="w-3"></span>
+                  {/if}
+                  <span>{size}</span>
+                </button>
+              {/each}
+            </div>
+          </div>
+        {/if}
+      </div>
+    {/if}

    <!-- Quality -->
    <div class="flex items-center gap-1.5">
@@ -310,7 +311,7 @@

        <!-- Dropdown Panel - fixed positioning to escape overflow:hidden -->
        <div
-          class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto overflow-x-hidden min-w-max"
+          class="fixed bg-exo-dark-gray border border-exo-yellow/30 rounded shadow-lg shadow-black/50 z-[9999] max-h-48 overflow-y-auto min-w-max"
          style="bottom: calc(100vh - {qualityDropdownPosition()
            .top}px + 4px); left: {qualityDropdownPosition().left}px;"
        >
--- a/dashboard/src/lib/stores/app.svelte.ts
+++ b/dashboard/src/lib/stores/app.svelte.ts
@@ -306,14 +306,13 @@ const IMAGE_PARAMS_STORAGE_KEY = "exo-image-generation-params";
 export interface ImageGenerationParams {
  // Basic params
  size:
-    | "auto"
    | "512x512"
    | "768x768"
    | "1024x1024"
    | "1024x768"
    | "768x1024"
-    | "1024x1536"
-    | "1536x1024";
+    | "1024x1365"
+    | "1365x1024";
  quality: "low" | "medium" | "high";
  outputFormat: "png" | "jpeg";
  numImages: number;
@@ -337,7 +336,7 @@ export interface EditingImage {
 }

 const DEFAULT_IMAGE_PARAMS: ImageGenerationParams = {
-  size: "auto",
+  size: "1024x1024",
  quality: "medium",
  outputFormat: "png",
  numImages: 1,
--- a/dashboard/src/lib/stores/theme.svelte.ts
+++ b/dashboard/src/lib/stores/theme.svelte.ts
@@ -1,28 +0,0 @@
-import { browser } from "$app/environment";
-
-let _isLight = $state(false);
-
-export const theme = {
-  get isLight() {
-    return _isLight;
-  },
-
-  init() {
-    if (!browser) return;
-    _isLight = document.documentElement.classList.contains("light");
-  },
-
-  toggle() {
-    if (!browser) return;
-    _isLight = !_isLight;
-    if (_isLight) {
-      document.documentElement.classList.remove("dark");
-      document.documentElement.classList.add("light");
-      localStorage.setItem("exo-theme", "light");
-    } else {
-      document.documentElement.classList.remove("light");
-      document.documentElement.classList.add("dark");
-      localStorage.setItem("exo-theme", "dark");
-    }
-  },
-};
--- a/dashboard/src/routes/+layout.svelte
+++ b/dashboard/src/routes/+layout.svelte
@@ -1,13 +1,7 @@
 <script lang="ts">
  import "../app.css";
-  import { onMount } from "svelte";
-  import { theme } from "$lib/stores/theme.svelte";

  let { children } = $props();
-
-  onMount(() => {
-    theme.init();
-  });
 </script>

 <svelte:head>
--- a/flake.nix
+++ b/flake.nix
@@ -115,7 +115,7 @@
          packages = lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin (
            let
              uvLock = builtins.fromTOML (builtins.readFile ./uv.lock);
-              mlxPackage = builtins.head (builtins.filter (p: p.name == "mlx" && p.source ? git) uvLock.package);
+              mlxPackage = builtins.head (builtins.filter (p: p.name == "mlx") uvLock.package);
              uvLockMlxVersion = mlxPackage.version;
            in
            {
--- a/nix/mlx.nix
+++ b/nix/mlx.nix
@@ -41,16 +41,16 @@ let

  mlx = stdenv.mkDerivation rec {
    pname = "mlx";
-    version = let v = "0.30.7.dev20260218+14841977"; in
+    version = let v = "0.30.6"; in
      assert v == uvLockMlxVersion || throw "MLX version mismatch: nix/mlx.nix has ${v} but uv.lock has ${uvLockMlxVersion}. Update both the version and hash in nix/mlx.nix.";
      v;
    pyproject = true;

    src = fetchFromGitHub {
-      owner = "rltakashige";
-      repo = "mlx-jaccl-fix-small-recv";
-      rev = "1484197707f35186ad3bd614357c7c47fdf86ebc";
-      hash = "sha256-FupCMoK/SF/ldfKuvMSAKECcOP8c+ANgkQlPZttDsLk=";
+      owner = "ml-explore";
+      repo = "mlx";
+      tag = "v${version}";
+      hash = "sha256-avD5EGhwgmPdXLAyQSqTO6AXk/W3ziH+f6AetjK3Sdo=";
    };

    patches = [
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -17,9 +17,9 @@ dependencies = [
    "loguru>=0.7.3",
    "exo_pyo3_bindings", # rust bindings
    "anyio==4.11.0",
-    "mlx; sys_platform == 'darwin'",
+    "mlx==0.30.6; sys_platform == 'darwin'",
    "mlx[cpu]==0.30.6; sys_platform == 'linux'",
-    "mlx-lm==0.30.7",
+    "mlx-lm==0.30.6",
    "tiktoken>=0.12.0", # required for kimi k2 tokenizer
    "hypercorn>=0.18.0",
    "openai-harmony>=0.0.8",
@@ -64,7 +64,6 @@ members = [

 [tool.uv.sources]
 exo_pyo3_bindings = { workspace = true }
-mlx = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git", branch = "address-rdma-gpu-locks", marker = "sys_platform == 'darwin'" }
 #mlx-lm = { git = "https://github.com/davidmcc73/mlx-lm", branch = "stable" }
 # Uncomment to use local mlx/mlx-lm development versions:
 # mlx = { path = "/Users/Shared/mlx", editable=true }
--- a/python/parts.nix
+++ b/python/parts.nix
@@ -58,21 +58,6 @@
        lib.optionalAttrs pkgs.stdenv.hostPlatform.isLinux (
          (lib.mapAttrs (_: ignoreMissing) nvidiaPackages) // {
            mlx = ignoreMissing prev.mlx;
-            mlx-cuda-13 = prev.mlx-cuda-13.overrideAttrs (old: {
-              buildInputs = (old.buildInputs or [ ]) ++ [
-                final.nvidia-cublas
-                final.nvidia-cuda-nvrtc
-                final.nvidia-cudnn-cu13
-                final.nvidia-nccl-cu13
-              ];
-              preFixup = ''
-                addAutoPatchelfSearchPath ${final.nvidia-cublas}
-                addAutoPatchelfSearchPath ${final.nvidia-cuda-nvrtc}
-                addAutoPatchelfSearchPath ${final.nvidia-cudnn-cu13}
-                addAutoPatchelfSearchPath ${final.nvidia-nccl-cu13}
-              '';
-              autoPatchelfIgnoreMissingDeps = [ "libcuda.so.1" ];
-            });
            torch = ignoreMissing prev.torch;
            triton = ignoreMissing prev.triton;
          }
@@ -89,25 +74,14 @@
          linuxOverlay
        ]
      );
-      # mlx-cpu and mlx-cuda-13 both ship mlx/ site-packages files; keep first.
-      # mlx-cpu/mlx-cuda-13 and nvidia-cudnn-cu12/cu13 ship overlapping files.
-      venvCollisionPaths = lib.optionals pkgs.stdenv.hostPlatform.isLinux [
-        "lib/python3.13/site-packages/mlx*"
-        "lib/python3.13/site-packages/nvidia*"
-      ];
-
-      exoVenv = (pythonSet.mkVirtualEnv "exo-env" workspace.deps.default).overrideAttrs {
-        venvIgnoreCollisions = venvCollisionPaths;
-      };
+      exoVenv = pythonSet.mkVirtualEnv "exo-env" workspace.deps.default;

      # Virtual environment with dev dependencies for testing
-      testVenv = (pythonSet.mkVirtualEnv "exo-test-env" (
+      testVenv = pythonSet.mkVirtualEnv "exo-test-env" (
        workspace.deps.default // {
          exo = [ "dev" ]; # Include pytest, pytest-asyncio, pytest-env
        }
-      )).overrideAttrs {
-        venvIgnoreCollisions = venvCollisionPaths;
-      };
+      );

      mkPythonScript = name: path: pkgs.writeShellApplication {
        inherit name;
--- a/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "deepseek"
 quantization = "4bit"
 base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 405874409472
--- a/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--DeepSeek-V3.1-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "deepseek"
 quantization = "8bit"
 base_model = "DeepSeek V3.1"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 765577920512
--- a/resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.5-Air-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "8bit"
 base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 122406567936
--- a/resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.5-Air-bf16.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "bf16"
 base_model = "GLM 4.5 Air"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 229780750336
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "4bit"
 base_model = "GLM 4.7"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 198556925568
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-6bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "6bit"
 base_model = "GLM 4.7"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 286737579648
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-8bit-gs32.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "8bit"
 base_model = "GLM 4.7"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 396963397248
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "4bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 19327352832
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-5bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "5bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 22548578304
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-6bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "6bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 26843545600
--- a/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-4.7-Flash-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "glm"
 quantization = "8bit"
 base_model = "GLM 4.7 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 34359738368
--- a/resources/inference_model_cards/mlx-community--GLM-5-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-5-8bit.toml
@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-5-8bit-MXFP8"
-n_layers = 78
-hidden_size = 6144
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "8bit"
-base_model = "GLM-5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 790517400864
--- a/resources/inference_model_cards/mlx-community--GLM-5-MXFP4-Q8.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-5-MXFP4-Q8.toml
@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-5-MXFP4-Q8"
-n_layers = 78
-hidden_size = 6144
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "MXFP4-Q8"
-base_model = "GLM-5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 405478939008
--- a/resources/inference_model_cards/mlx-community--GLM-5-bf16.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-5-bf16.toml
@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-5"
-n_layers = 78
-hidden_size = 6144
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "bf16"
-base_model = "GLM-5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 1487822475264
--- a/resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml
+++ b/resources/inference_model_cards/mlx-community--Kimi-K2-Thinking.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "kimi"
 quantization = ""
 base_model = "Kimi K2"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 706522120192
--- a/resources/inference_model_cards/mlx-community--Kimi-K2.5.toml
+++ b/resources/inference_model_cards/mlx-community--Kimi-K2.5.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "kimi"
 quantization = ""
 base_model = "Kimi K2.5"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 662498705408
--- a/resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml
+++ b/resources/inference_model_cards/mlx-community--MiniMax-M2.1-3bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "minimax"
 quantization = "3bit"
 base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 100086644736
--- a/resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--MiniMax-M2.1-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "minimax"
 quantization = "8bit"
 base_model = "MiniMax M2.1"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 242986745856
--- a/resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-0.6B-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 342884352
--- a/resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-0.6B-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 0.6B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 698351616
--- a/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 235B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 141733920768
--- a/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-235B-A22B-Instruct-2507-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 235B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 268435456000
--- a/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 30B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 17612931072
--- a/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-30B-A3B-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 30B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 33279705088
--- a/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "4bit"
 base_model = "Qwen3 Next 80B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 47080074240
--- a/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--Qwen3-Next-80B-A3B-Thinking-8bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "qwen"
 quantization = "8bit"
 base_model = "Qwen3 Next 80B"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 88814387200
--- a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml
+++ b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-4bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "step"
 quantization = "4bit"
 base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 114572190076
--- a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml
+++ b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-6bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "step"
 quantization = "6bit"
 base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 159039627774
--- a/resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml
+++ b/resources/inference_model_cards/mlx-community--Step-3.5-Flash-8Bit.toml
@@ -6,7 +6,7 @@ tasks = ["TextGeneration"]
 family = "step"
 quantization = "8bit"
 base_model = "Step 3.5 Flash"
-capabilities = ["text", "thinking", "thinking_toggle"]
+capabilities = ["text", "thinking"]

 [storage_size]
 in_bytes = 209082699847
--- a/rust/exo_pyo3_bindings/Cargo.toml
+++ b/rust/exo_pyo3_bindings/Cargo.toml
@@ -25,17 +25,17 @@ workspace = true
 networking = { workspace = true }

 # interop
-pyo3 = { version = "0.27.2", features = [
-    # "abi3-py313", # tells pyo3 (and maturin) to build using the stable ABI with minimum Python version 3.13
+pyo3 = { version = "0.27.1", features = [
+    # "abi3-py311", # tells pyo3 (and maturin) to build using the stable ABI with minimum Python version 3.11
    "nightly", # enables better-supported GIL integration
    "experimental-async", # async support in #[pyfunction] & #[pymethods]
    #"experimental-inspect", # inspection of generated binary => easier to automate type-hint generation
    #"py-clone", # adding Clone-ing of `Py<T>` without GIL (may cause panics - remove if panics happen)
-    # "multiple-pymethods", # allows multiple #[pymethods] sections per class
+    "multiple-pymethods", # allows multiple #[pymethods] sections per class

    # integrations with other libraries
-    # "arc_lock", "bigdecimal", "either", "hashbrown", "indexmap", "num-bigint", "num-complex", "num-rational",
-    # "ordered-float", "rust_decimal", "smallvec",
+    "arc_lock", "bigdecimal", "either", "hashbrown", "indexmap", "num-bigint", "num-complex", "num-rational",
+    "ordered-float", "rust_decimal", "smallvec",
    # "anyhow", "chrono", "chrono-local", "chrono-tz", "eyre", "jiff-02", "lock_api", "parking-lot", "time",  "serde",
 ] }
 pyo3-stub-gen = { version = "0.17.2" }
@@ -45,6 +45,8 @@ pyo3-log = "0.13.2"
 # macro dependencies
 extend = { workspace = true }
 delegate = { workspace = true }
+impl-trait-for-tuples = { workspace = true }
+derive_more = { workspace = true }
 pin-project = { workspace = true }

 # async runtime
@@ -52,11 +54,24 @@ tokio = { workspace = true, features = ["full", "tracing"] }
 futures = { workspace = true }

 # utility dependencies
+once_cell = "1.21.3"
+thread_local = "1.1.9"
 util = { workspace = true }
+thiserror = { workspace = true }
+#internment = { workspace = true }
+#recursion = { workspace = true }
+#generativity = { workspace = true }
+#itertools = { workspace = true }
+

 # Tracing
+#tracing = "0.1"
+#tracing-subscriber = "0.3"
+#console-subscriber = "0.1.5"
+#tracing-log = "0.2.0"
 log = { workspace = true }
 env_logger = "0.11"

+
 # Networking
 libp2p = { workspace = true, features = ["full"] }
--- a/rust/exo_pyo3_bindings/src/allow_threading.rs
+++ b/rust/exo_pyo3_bindings/src/allow_threading.rs
@@ -6,7 +6,7 @@ use pyo3::marker::Ungil;
 use pyo3::prelude::*;
 use std::{
    future::Future,
-    pin::Pin,
+    pin::{Pin, pin},
    task::{Context, Poll},
 };

@@ -33,6 +33,8 @@ where

    fn poll(self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Self::Output> {
        let waker = cx.waker();
-        Python::attach(|py| py.detach(|| self.project().0.poll(&mut Context::from_waker(waker))))
+        Python::with_gil(|py| {
+            py.allow_threads(|| self.project().0.poll(&mut Context::from_waker(waker)))
+        })
    }
 }
--- a/rust/exo_pyo3_bindings/src/examples/mod.rs
+++ b/rust/exo_pyo3_bindings/src/examples/mod.rs
@@ -0,0 +1,240 @@
+//! This module exists to hold examples of some pyo3 patterns that may be too complex to
+//! re-create from scratch, but too inhomogenous to create an abstraction/wrapper around.
+//!
+//! Pattern examples include:
+//!  - Async task handles: with GC-integrated cleanup
+//!  - Sync/async callbacks from python: with propper eventloop handling
+//!
+//! Mutability pattern: https://pyo3.rs/v0.26.0/async-await.html#send--static-constraint
+//!  - Store mutable fields in tokio's `Mutex<T>`
+//!  - For async code: take `&self` and `.lock().await`
+//!  - For sync code: take `&mut self` and `.get_mut()`
+
+use crate::ext::{PyResultExt as _, ResultExt as _, TokioRuntimeExt as _};
+use futures::FutureExt as _;
+use futures::future::BoxFuture;
+use pyo3::exceptions::PyRuntimeError;
+use pyo3::prelude::{PyModule, PyModuleMethods as _};
+use pyo3::{
+    Bound, Py, PyAny, PyErr, PyResult, PyTraverseError, PyVisit, Python, pyclass, pymethods,
+};
+use std::time::Duration;
+use tokio::sync::mpsc;
+use tokio::sync::mpsc::error::TryRecvError;
+
+fn needs_tokio_runtime() {
+    tokio::runtime::Handle::current();
+}
+
+type SyncCallback = Box<dyn Fn() + Send + Sync>;
+type AsyncCallback = Box<dyn Fn() -> BoxFuture<'static, ()> + Send + Sync>;
+
+enum AsyncTaskMessage {
+    SyncCallback(SyncCallback),
+    AsyncCallback(AsyncCallback),
+}
+
+async fn async_task(
+    sender: mpsc::UnboundedSender<()>,
+    mut receiver: mpsc::UnboundedReceiver<AsyncTaskMessage>,
+) {
+    log::info!("RUST: async task started");
+
+    // task state
+    let mut interval = tokio::time::interval(Duration::from_secs(1));
+
+    let mut sync_cbs: Vec<SyncCallback> = vec![];
+    let mut async_cbs: Vec<AsyncCallback> = vec![];
+
+    loop {
+        tokio::select! {
+            // handle incoming messages from task-handle
+            message = receiver.recv() => {
+                // handle closed channel by exiting
+                let Some(message) = message else {
+                    log::info!("RUST: channel closed");
+                    break;
+                };
+
+                // dispatch incoming event
+                match message {
+                    AsyncTaskMessage::SyncCallback(cb) => {
+                        sync_cbs.push(cb);
+                    }
+                    AsyncTaskMessage::AsyncCallback(cb) => {
+                        async_cbs.push(cb);
+                    }
+                }
+            }
+
+            // handle all other events
+            _ = interval.tick() => {
+                log::info!("RUST: async task tick");
+
+                // call back all sync callbacks
+                for cb in &sync_cbs {
+                    cb();
+                }
+
+                // call back all async callbacks
+                for cb in &async_cbs {
+                    cb().await;
+                }
+
+                // send event on unbounded channel
+                sender.send(()).expect("handle receiver cannot be closed/dropped");
+            }
+        }
+    }
+
+    log::info!("RUST: async task stopped");
+}
+
+// #[gen_stub_pyclass]
+#[pyclass(name = "AsyncTaskHandle")]
+#[derive(Debug)]
+struct PyAsyncTaskHandle {
+    sender: Option<mpsc::UnboundedSender<AsyncTaskMessage>>,
+    receiver: mpsc::UnboundedReceiver<()>,
+}
+
+#[allow(clippy::expect_used)]
+impl PyAsyncTaskHandle {
+    const fn sender(&self) -> &mpsc::UnboundedSender<AsyncTaskMessage> {
+        self.sender
+            .as_ref()
+            .expect("The sender should only be None after de-initialization.")
+    }
+
+    const fn sender_mut(&mut self) -> &mpsc::UnboundedSender<AsyncTaskMessage> {
+        self.sender
+            .as_mut()
+            .expect("The sender should only be None after de-initialization.")
+    }
+
+    const fn new(
+        sender: mpsc::UnboundedSender<AsyncTaskMessage>,
+        receiver: mpsc::UnboundedReceiver<()>,
+    ) -> Self {
+        Self {
+            sender: Some(sender),
+            receiver,
+        }
+    }
+}
+
+// #[gen_stub_pymethods]
+#[pymethods]
+impl PyAsyncTaskHandle {
+    #[new]
+    fn py_new(py: Python<'_>) -> PyResult<Self> {
+        use pyo3_async_runtimes::tokio::get_runtime;
+
+        // create communication channel TOWARDS our task
+        let (h_sender, t_receiver) = mpsc::unbounded_channel::<AsyncTaskMessage>();
+
+        // create communication channel FROM our task
+        let (t_sender, h_receiver) = mpsc::unbounded_channel::<()>();
+
+        // perform necessary setup within tokio context - or it crashes
+        let () = get_runtime().block_on(async { needs_tokio_runtime() });
+
+        // spawn tokio task with this thread's task-locals - without this, async callbacks on the new threads will not work!!
+        _ = get_runtime().spawn_with_scope(py, async move {
+            async_task(t_sender, t_receiver).await;
+        });
+        Ok(Self::new(h_sender, h_receiver))
+    }
+
+    /// NOTE: exceptions in callbacks are silently ignored until end of execution
+    fn add_sync_callback(
+        &self,
+        // #[gen_stub(override_type(
+        //     type_repr="collections.abc.Callable[[], None]",
+        //     imports=("collections.abc")
+        // ))]
+        callback: Py<PyAny>,
+    ) -> PyResult<()> {
+        // blocking call to async method -> can do non-blocking if needed
+        self.sender()
+            .send(AsyncTaskMessage::SyncCallback(Box::new(move || {
+                _ = Python::with_gil(|py| callback.call0(py).write_unraisable_with(py));
+            })))
+            .pyerr()?;
+        Ok(())
+    }
+
+    /// NOTE: exceptions in callbacks are silently ignored until end of execution
+    fn add_async_callback(
+        &self,
+        // #[gen_stub(override_type(
+        //     type_repr="collections.abc.Callable[[], collections.abc.Awaitable[None]]",
+        //     imports=("collections.abc")
+        // ))]
+        callback: Py<PyAny>,
+    ) -> PyResult<()> {
+        // blocking call to async method -> can do non-blocking if needed
+        self.sender()
+            .send(AsyncTaskMessage::AsyncCallback(Box::new(move || {
+                let c = Python::with_gil(|py| callback.clone_ref(py));
+                async move {
+                    if let Some(f) = Python::with_gil(|py| {
+                        let coroutine = c.call0(py).write_unraisable_with(py)?;
+                        pyo3_async_runtimes::tokio::into_future(coroutine.into_bound(py))
+                            .write_unraisable_with(py)
+                    }) {
+                        _ = f.await.write_unraisable();
+                    }
+                }
+                .boxed()
+            })))
+            .pyerr()?;
+        Ok(())
+    }
+
+    async fn receive_unit(&mut self) -> PyResult<()> {
+        self.receiver
+            .recv()
+            .await
+            .ok_or(PyErr::new::<PyRuntimeError, _>(
+                "cannot receive unit on closed channel",
+            ))
+    }
+
+    fn drain_units(&mut self) -> PyResult<i32> {
+        let mut cnt = 0;
+        loop {
+            match self.receiver.try_recv() {
+                Err(TryRecvError::Disconnected) => {
+                    return Err(PyErr::new::<PyRuntimeError, _>(
+                        "cannot receive unit on closed channel",
+                    ));
+                }
+                Err(TryRecvError::Empty) => return Ok(cnt),
+                Ok(()) => {
+                    cnt += 1;
+                    continue;
+                }
+            }
+        }
+    }
+
+    // #[gen_stub(skip)]
+    const fn __traverse__(&self, _visit: PyVisit<'_>) -> Result<(), PyTraverseError> {
+        Ok(()) // This is needed purely so `__clear__` can work
+    }
+
+    // #[gen_stub(skip)]
+    fn __clear__(&mut self) {
+        // TODO: may or may not need to await a "kill-signal" oneshot channel message,
+        //       to ensure that the networking task is done BEFORE exiting the clear function...
+        //       but this may require GIL?? and it may not be safe to call GIL here??
+        self.sender = None; // Using Option<T> as a trick to force `sender` channel to be dropped
+    }
+}
+
+pub fn examples_submodule(m: &Bound<'_, PyModule>) -> PyResult<()> {
+    m.add_class::<PyAsyncTaskHandle>()?;
+
+    Ok(())
+}
--- a/rust/exo_pyo3_bindings/src/lib.rs
+++ b/rust/exo_pyo3_bindings/src/lib.rs
@@ -17,6 +17,7 @@

 extern crate core;
 mod allow_threading;
+mod examples;
 pub(crate) mod networking;
 pub(crate) mod pylibp2p;

@@ -24,6 +25,7 @@ use crate::networking::networking_submodule;
 use crate::pylibp2p::ident::ident_submodule;
 use crate::pylibp2p::multiaddr::multiaddr_submodule;
 use pyo3::prelude::PyModule;
+use pyo3::prelude::*;
 use pyo3::{Bound, PyResult, pyclass, pymodule};
 use pyo3_stub_gen::define_stub_info_gatherer;

@@ -34,10 +36,14 @@ pub(crate) mod r#const {

 /// Namespace for all the type/trait aliases used by this crate.
 pub(crate) mod alias {
+    use std::error::Error;
    use std::marker::Tuple;

    pub trait SendFn<Args: Tuple + Send + 'static, Output> =
        Fn<Args, Output = Output> + Send + 'static;
+
+    pub type AnyError = Box<dyn Error + Send + Sync + 'static>;
+    pub type AnyResult<T> = Result<T, AnyError>;
 }

 /// Namespace for crate-wide extension traits/methods
@@ -45,6 +51,7 @@ pub(crate) mod ext {
    use crate::allow_threading::AllowThreads;
    use extend::ext;
    use pyo3::exceptions::{PyConnectionError, PyRuntimeError};
+    use pyo3::marker::Ungil;
    use pyo3::types::PyBytes;
    use pyo3::{Py, PyErr, PyResult, Python};
    use tokio::runtime::Runtime;
@@ -55,7 +62,7 @@ pub(crate) mod ext {
    #[ext(pub, name = ByteArrayExt)]
    impl [u8] {
        fn pybytes(&self) -> Py<PyBytes> {
-            Python::attach(|py| PyBytes::new(py, self).unbind())
+            Python::with_gil(|py| PyBytes::new(py, self).unbind())
        }
    }

@@ -91,7 +98,7 @@ pub(crate) mod ext {
    #[ext(pub, name = PyResultExt)]
    impl<T> PyResult<T> {
        fn write_unraisable(self) -> Option<T> {
-            Python::attach(|py| self.write_unraisable_with(py))
+            Python::with_gil(|py| self.write_unraisable_with(py))
        }

        fn write_unraisable_with(self, py: Python<'_>) -> Option<T> {
@@ -168,6 +175,24 @@ pub(crate) mod ext {
    }
 }

+pub(crate) mod private {
+    use std::marker::Sized;
+
+    /// Sealed traits support
+    pub trait Sealed {}
+    impl<T: ?Sized> Sealed for T {}
+}
+
+/// A wrapper around [`Py`] that implements [`Clone`] using [`Python::with_gil`].
+#[repr(transparent)]
+pub(crate) struct ClonePy<T>(pub Py<T>);
+
+impl<T> Clone for ClonePy<T> {
+    fn clone(&self) -> Self {
+        Python::with_gil(|py| Self(self.0.clone_ref(py)))
+    }
+}
+
 /// A Python module implemented in Rust. The name of this function must match
 /// the `lib.name` setting in the `Cargo.toml`, else Python will not be able to
 /// import the module.
--- a/rust/exo_pyo3_bindings/src/networking.rs
+++ b/rust/exo_pyo3_bindings/src/networking.rs
@@ -11,9 +11,9 @@ use crate::ext::{ResultExt as _, TokioMpscReceiverExt as _, TokioMpscSenderExt a
 use crate::pyclass;
 use crate::pylibp2p::ident::{PyKeypair, PyPeerId};
 use libp2p::futures::StreamExt as _;
-use libp2p::gossipsub;
 use libp2p::gossipsub::{IdentTopic, Message, MessageId, PublishError};
 use libp2p::swarm::SwarmEvent;
+use libp2p::{gossipsub, mdns};
 use networking::discovery;
 use networking::swarm::create_swarm;
 use pyo3::prelude::{PyModule, PyModuleMethods as _};
@@ -25,7 +25,7 @@ use tokio::sync::{Mutex, mpsc, oneshot};

 mod exception {
    use pyo3::types::PyTuple;
-    use pyo3::{exceptions::PyException, prelude::*};
+    use pyo3::{PyErrArguments, exceptions::PyException, prelude::*};
    use pyo3_stub_gen::derive::*;

    #[gen_stub_pyclass]
@@ -155,6 +155,7 @@ async fn networking_task(
 ) {
    use SwarmEvent::*;
    use ToTask::*;
+    use mdns::Event::*;
    use networking::swarm::BehaviourEvent::*;

    log::info!("RUST: networking task started");
@@ -484,7 +485,7 @@ impl PyNetworkingHandle {
        let (tx, rx) = oneshot::channel();

        // send off request to subscribe
-        let data = Python::attach(|py| Vec::from(data.as_bytes(py)));
+        let data = Python::with_gil(|py| Vec::from(data.as_bytes(py)));
        self.to_task_tx()
            .send_py(ToTask::GossipsubPublish {
                topic,
--- a/rust/networking/Cargo.toml
+++ b/rust/networking/Cargo.toml
@@ -19,6 +19,8 @@ either = { workspace = true }
 # macro dependencies
 extend = { workspace = true }
 delegate = { workspace = true }
+impl-trait-for-tuples = { workspace = true }
+derive_more = { workspace = true }

 # async
 tokio = { workspace = true, features = ["full"] }
@@ -27,6 +29,11 @@ futures-timer = { workspace = true }

 # utility dependencies
 util = { workspace = true }
+thiserror = { workspace = true }
+#internment = { workspace = true }
+#recursion = { workspace = true }
+#generativity = { workspace = true }
+#itertools = { workspace = true }
 tracing-subscriber = { version = "0.3.19", features = ["default", "env-filter"] }
 keccak-const = { workspace = true }

@@ -34,4 +41,4 @@ keccak-const = { workspace = true }
 log = { workspace = true }

 # networking
-libp2p = { workspace = true, features = ["full"] }
+libp2p = { workspace = true, features = ["full"] }
--- a/rust/networking/examples/chatroom_manual.rs
+++ b/rust/networking/examples/chatroom_manual.rs
@@ -24,8 +24,8 @@ use libp2p::{
    swarm::{NetworkBehaviour, SwarmEvent},
    tcp, yamux,
 };
-use std::error::Error;
 use std::time::Duration;
+use std::{error::Error, hash::Hash};
 use tokio::{io, io::AsyncBufReadExt, select};
 use tracing_subscriber::EnvFilter;

--- a/rust/networking/src/discovery.rs
+++ b/rust/networking/src/discovery.rs
@@ -1,4 +1,5 @@
 use crate::ext::MultiaddrExt;
+use crate::keep_alive;
 use delegate::delegate;
 use either::Either;
 use futures::FutureExt;
--- a/rust/networking/src/keep_alive.rs
+++ b/rust/networking/src/keep_alive.rs
@@ -0,0 +1,44 @@
+use delegate::delegate;
+use libp2p::swarm::handler::ConnectionEvent;
+use libp2p::swarm::{ConnectionHandlerEvent, SubstreamProtocol, dummy, handler};
+use std::task::{Context, Poll};
+
+/// An implementation of [`ConnectionHandler`] that doesn't handle any protocols, but it keeps
+/// the connection alive.
+#[derive(Clone)]
+#[repr(transparent)]
+pub struct ConnectionHandler(dummy::ConnectionHandler);
+
+impl ConnectionHandler {
+    pub fn new() -> Self {
+        ConnectionHandler(dummy::ConnectionHandler)
+    }
+}
+
+impl handler::ConnectionHandler for ConnectionHandler {
+    // delegate types and implementation mostly to dummy handler
+    type FromBehaviour = <dummy::ConnectionHandler as handler::ConnectionHandler>::FromBehaviour;
+    type ToBehaviour = <dummy::ConnectionHandler as handler::ConnectionHandler>::ToBehaviour;
+    type InboundProtocol =
+        <dummy::ConnectionHandler as handler::ConnectionHandler>::InboundProtocol;
+    type OutboundProtocol =
+        <dummy::ConnectionHandler as handler::ConnectionHandler>::OutboundProtocol;
+    type InboundOpenInfo =
+        <dummy::ConnectionHandler as handler::ConnectionHandler>::InboundOpenInfo;
+    type OutboundOpenInfo =
+        <dummy::ConnectionHandler as handler::ConnectionHandler>::OutboundOpenInfo;
+
+    delegate! {
+        to self.0 {
+            fn listen_protocol(&self) -> SubstreamProtocol<Self::InboundProtocol, Self::InboundOpenInfo>;
+            fn poll(&mut self, cx: &mut Context<'_>) -> Poll<ConnectionHandlerEvent<Self::OutboundProtocol, Self::OutboundOpenInfo, Self::ToBehaviour>>;
+            fn on_behaviour_event(&mut self, event: Self::FromBehaviour);
+            fn on_connection_event(&mut self, event: ConnectionEvent<Self::InboundProtocol, Self::OutboundProtocol, Self::InboundOpenInfo, Self::OutboundOpenInfo>);
+        }
+    }
+
+    // specifically override this to force connection to stay alive
+    fn connection_keep_alive(&self) -> bool {
+        true
+    }
+}
--- a/rust/networking/src/lib.rs
+++ b/rust/networking/src/lib.rs
@@ -3,7 +3,19 @@
 //! this is here as a placeholder documentation
 //!
 //!
+
+// enable Rust-unstable features for convenience
+#![feature(trait_alias)]
+// #![feature(stmt_expr_attributes)]
+// #![feature(unboxed_closures)]
+// #![feature(assert_matches)]
+// #![feature(async_fn_in_dyn_trait)]
+// #![feature(async_for_loop)]
+// #![feature(auto_traits)]
+// #![feature(negative_impls)]
+
 pub mod discovery;
+pub mod keep_alive;
 pub mod swarm;

 /// Namespace for all the type/trait aliases used by this crate.
@@ -42,3 +54,11 @@ pub(crate) mod ext {
        }
    }
 }
+
+pub(crate) mod private {
+    #![allow(dead_code)]
+
+    /// Sealed traits support
+    pub trait Sealed {}
+    impl<T: ?Sized> Sealed for T {}
+}
--- a/src/exo/download/coordinator.py
+++ b/src/exo/download/coordinator.py
@@ -47,7 +47,6 @@ class DownloadCoordinator:
    download_command_receiver: Receiver[ForwarderDownloadCommand]
    local_event_sender: Sender[ForwarderEvent]
    event_index_counter: Iterator[int]
-    offline: bool = False

    # Local state
    download_status: dict[ModelId, DownloadProgress] = field(default_factory=dict)
@@ -63,8 +62,6 @@ class DownloadCoordinator:

    def __post_init__(self) -> None:
        self.event_sender, self.event_receiver = channel[Event]()
-        if self.offline:
-            self.shard_downloader.set_internet_connection(False)
        self.shard_downloader.on_progress(self._download_progress_callback)

    def _model_dir(self, model_id: ModelId) -> str:
@@ -110,17 +107,13 @@ class DownloadCoordinator:
            self._last_progress_time[model_id] = current_time()

    async def run(self) -> None:
-        logger.info(
-            f"Starting DownloadCoordinator{' (offline mode)' if self.offline else ''}"
-        )
-        if not self.offline:
-            self._test_internet_connection()
+        logger.info("Starting DownloadCoordinator")
+        self._test_internet_connection()
        async with self._tg as tg:
            tg.start_soon(self._command_processor)
            tg.start_soon(self._forward_events)
            tg.start_soon(self._emit_existing_download_progress)
-            if not self.offline:
-                tg.start_soon(self._check_internet_connection)
+            tg.start_soon(self._check_internet_connection)

    def _test_internet_connection(self) -> None:
        try:
@@ -209,20 +202,6 @@ class DownloadCoordinator:
            )
            return

-        if self.offline:
-            logger.warning(
-                f"Offline mode: model {model_id} is not fully available locally, cannot download"
-            )
-            failed = DownloadFailed(
-                shard_metadata=shard,
-                node_id=self.node_id,
-                error_message=f"Model files not found locally in offline mode: {model_id}",
-                model_directory=self._model_dir(model_id),
-            )
-            self.download_status[model_id] = failed
-            await self.event_sender.send(NodeDownloadProgress(download_progress=failed))
-            return
-
        # Start actual download
        self._start_download_task(shard, initial_progress)

--- a/src/exo/download/download_utils.py
+++ b/src/exo/download/download_utils.py
@@ -448,13 +448,12 @@ async def download_file_with_retry(
    target_dir: Path,
    on_progress: Callable[[int, int, bool], None] = lambda _, __, ___: None,
    on_connection_lost: Callable[[], None] = lambda: None,
-    skip_internet: bool = False,
 ) -> Path:
    n_attempts = 3
    for attempt in range(n_attempts):
        try:
            return await _download_file(
-                model_id, revision, path, target_dir, on_progress, skip_internet
+                model_id, revision, path, target_dir, on_progress
            )
        except HuggingFaceAuthenticationError:
            raise
@@ -488,14 +487,10 @@ async def _download_file(
    path: str,
    target_dir: Path,
    on_progress: Callable[[int, int, bool], None] = lambda _, __, ___: None,
-    skip_internet: bool = False,
 ) -> Path:
    target_path = target_dir / path

    if await aios.path.exists(target_path):
-        if skip_internet:
-            return target_path
-
        local_size = (await aios.stat(target_path)).st_size

        # Try to verify against remote, but allow offline operation
@@ -515,11 +510,6 @@ async def _download_file(
            )
            return target_path

-    if skip_internet:
-        raise FileNotFoundError(
-            f"File {path} not found locally and cannot download in offline mode"
-        )
-
    await aios.makedirs((target_dir / path).parent, exist_ok=True)
    length, etag = await file_meta(model_id, revision, path)
    remote_hash = etag[:-5] if etag.endswith("-gzip") else etag
@@ -824,7 +814,6 @@ async def download_shard(
                    file, curr_bytes, total_bytes, is_renamed
                ),
                on_connection_lost=on_connection_lost,
-                skip_internet=skip_internet,
            )

    if not skip_download:
--- a/src/exo/download/tests/test_offline_mode.py
+++ b/src/exo/download/tests/test_offline_mode.py
@@ -1,230 +0,0 @@
-"""Tests for offline/air-gapped mode."""
-
-from collections.abc import AsyncIterator
-from pathlib import Path
-from unittest.mock import AsyncMock, patch
-
-import aiofiles
-import aiofiles.os as aios
-import pytest
-
-from exo.download.download_utils import (
-    _download_file,  # pyright: ignore[reportPrivateUsage]
-    download_file_with_retry,
-    fetch_file_list_with_cache,
-)
-from exo.shared.types.common import ModelId
-from exo.shared.types.worker.downloads import FileListEntry
-
-
-@pytest.fixture
-def model_id() -> ModelId:
-    return ModelId("test-org/test-model")
-
-
-@pytest.fixture
-async def temp_models_dir(tmp_path: Path) -> AsyncIterator[Path]:
-    models_dir = tmp_path / "models"
-    await aios.makedirs(models_dir, exist_ok=True)
-    with patch("exo.download.download_utils.EXO_MODELS_DIR", models_dir):
-        yield models_dir
-
-
-class TestDownloadFileOffline:
-    """Tests for _download_file with skip_internet=True."""
-
-    async def test_returns_local_file_without_http_verification(
-        self, model_id: ModelId, tmp_path: Path
-    ) -> None:
-        """When skip_internet=True and file exists locally, return it immediately
-        without making any HTTP calls (no file_meta verification)."""
-        target_dir = tmp_path / "downloads"
-        await aios.makedirs(target_dir, exist_ok=True)
-
-        local_file = target_dir / "model.safetensors"
-        async with aiofiles.open(local_file, "wb") as f:
-            await f.write(b"model weights data")
-
-        with patch(
-            "exo.download.download_utils.file_meta",
-            new_callable=AsyncMock,
-        ) as mock_file_meta:
-            result = await _download_file(
-                model_id,
-                "main",
-                "model.safetensors",
-                target_dir,
-                skip_internet=True,
-            )
-
-            assert result == local_file
-            mock_file_meta.assert_not_called()
-
-    async def test_raises_file_not_found_for_missing_file(
-        self, model_id: ModelId, tmp_path: Path
-    ) -> None:
-        """When skip_internet=True and file does NOT exist locally,
-        raise FileNotFoundError instead of attempting download."""
-        target_dir = tmp_path / "downloads"
-        await aios.makedirs(target_dir, exist_ok=True)
-
-        with pytest.raises(FileNotFoundError, match="offline mode"):
-            await _download_file(
-                model_id,
-                "main",
-                "missing_model.safetensors",
-                target_dir,
-                skip_internet=True,
-            )
-
-    async def test_returns_local_file_in_subdirectory(
-        self, model_id: ModelId, tmp_path: Path
-    ) -> None:
-        """When skip_internet=True and file exists in a subdirectory,
-        return it without HTTP calls."""
-        target_dir = tmp_path / "downloads"
-        subdir = target_dir / "transformer"
-        await aios.makedirs(subdir, exist_ok=True)
-
-        local_file = subdir / "diffusion_pytorch_model.safetensors"
-        async with aiofiles.open(local_file, "wb") as f:
-            await f.write(b"weights")
-
-        with patch(
-            "exo.download.download_utils.file_meta",
-            new_callable=AsyncMock,
-        ) as mock_file_meta:
-            result = await _download_file(
-                model_id,
-                "main",
-                "transformer/diffusion_pytorch_model.safetensors",
-                target_dir,
-                skip_internet=True,
-            )
-
-            assert result == local_file
-            mock_file_meta.assert_not_called()
-
-
-class TestDownloadFileWithRetryOffline:
-    """Tests for download_file_with_retry with skip_internet=True."""
-
-    async def test_propagates_skip_internet_to_download_file(
-        self, model_id: ModelId, tmp_path: Path
-    ) -> None:
-        """Verify skip_internet is passed through to _download_file."""
-        target_dir = tmp_path / "downloads"
-        await aios.makedirs(target_dir, exist_ok=True)
-
-        local_file = target_dir / "config.json"
-        async with aiofiles.open(local_file, "wb") as f:
-            await f.write(b'{"model_type": "qwen2"}')
-
-        with patch(
-            "exo.download.download_utils.file_meta",
-            new_callable=AsyncMock,
-        ) as mock_file_meta:
-            result = await download_file_with_retry(
-                model_id,
-                "main",
-                "config.json",
-                target_dir,
-                skip_internet=True,
-            )
-
-            assert result == local_file
-            mock_file_meta.assert_not_called()
-
-    async def test_file_not_found_does_not_retry(
-        self, model_id: ModelId, tmp_path: Path
-    ) -> None:
-        """FileNotFoundError from offline mode should not trigger retries."""
-        target_dir = tmp_path / "downloads"
-        await aios.makedirs(target_dir, exist_ok=True)
-
-        with pytest.raises(FileNotFoundError):
-            await download_file_with_retry(
-                model_id,
-                "main",
-                "nonexistent.safetensors",
-                target_dir,
-                skip_internet=True,
-            )
-
-
-class TestFetchFileListOffline:
-    """Tests for fetch_file_list_with_cache with skip_internet=True."""
-
-    async def test_uses_cached_file_list(
-        self, model_id: ModelId, temp_models_dir: Path
-    ) -> None:
-        """When skip_internet=True and cache file exists, use it without network."""
-        from pydantic import TypeAdapter
-
-        cache_dir = temp_models_dir / "caches" / model_id.normalize()
-        await aios.makedirs(cache_dir, exist_ok=True)
-
-        cached_list = [
-            FileListEntry(type="file", path="model.safetensors", size=1000),
-            FileListEntry(type="file", path="config.json", size=200),
-        ]
-        cache_file = cache_dir / f"{model_id.normalize()}--main--file_list.json"
-        async with aiofiles.open(cache_file, "w") as f:
-            await f.write(
-                TypeAdapter(list[FileListEntry]).dump_json(cached_list).decode()
-            )
-
-        with patch(
-            "exo.download.download_utils.fetch_file_list_with_retry",
-            new_callable=AsyncMock,
-        ) as mock_fetch:
-            result = await fetch_file_list_with_cache(
-                model_id, "main", skip_internet=True
-            )
-
-            assert result == cached_list
-            mock_fetch.assert_not_called()
-
-    async def test_falls_back_to_local_directory_scan(
-        self, model_id: ModelId, temp_models_dir: Path
-    ) -> None:
-        """When skip_internet=True and no cache but local files exist,
-        build file list from local directory."""
-        import json
-
-        model_dir = temp_models_dir / model_id.normalize()
-        await aios.makedirs(model_dir, exist_ok=True)
-
-        async with aiofiles.open(model_dir / "config.json", "w") as f:
-            await f.write('{"model_type": "qwen2"}')
-
-        index_data = {
-            "metadata": {},
-            "weight_map": {"model.layers.0.weight": "model.safetensors"},
-        }
-        async with aiofiles.open(model_dir / "model.safetensors.index.json", "w") as f:
-            await f.write(json.dumps(index_data))
-
-        async with aiofiles.open(model_dir / "model.safetensors", "wb") as f:
-            await f.write(b"x" * 500)
-
-        with patch(
-            "exo.download.download_utils.fetch_file_list_with_retry",
-            new_callable=AsyncMock,
-        ) as mock_fetch:
-            result = await fetch_file_list_with_cache(
-                model_id, "main", skip_internet=True
-            )
-
-            mock_fetch.assert_not_called()
-            paths = {entry.path for entry in result}
-            assert "config.json" in paths
-            assert "model.safetensors" in paths
-
-    async def test_raises_when_no_cache_and_no_local_files(
-        self, model_id: ModelId, temp_models_dir: Path
-    ) -> None:
-        """When skip_internet=True and neither cache nor local files exist,
-        raise FileNotFoundError."""
-        with pytest.raises(FileNotFoundError, match="No internet"):
-            await fetch_file_list_with_cache(model_id, "main", skip_internet=True)
--- a/src/exo/main.py
+++ b/src/exo/main.py
@@ -39,7 +39,6 @@ class Node:

    node_id: NodeId
    event_index_counter: Iterator[int]
-    offline: bool
    _tg: TaskGroup = field(init=False, default_factory=anyio.create_task_group)

    @classmethod
@@ -69,7 +68,6 @@ class Node:
                download_command_receiver=router.receiver(topics.DOWNLOAD_COMMANDS),
                local_event_sender=router.sender(topics.LOCAL_EVENTS),
                event_index_counter=event_index_counter,
-                offline=args.offline,
            )
        else:
            download_coordinator = None
@@ -134,13 +132,10 @@ class Node:
            api,
            node_id,
            event_index_counter,
-            args.offline,
        )

    async def run(self):
        async with self._tg as tg:
-            signal.signal(signal.SIGINT, lambda _, __: self.shutdown())
-            signal.signal(signal.SIGTERM, lambda _, __: self.shutdown())
            tg.start_soon(self.router.run)
            tg.start_soon(self.election.run)
            if self.download_coordinator:
@@ -152,6 +147,8 @@ class Node:
            if self.api:
                tg.start_soon(self.api.run)
            tg.start_soon(self._elect_loop)
+            signal.signal(signal.SIGINT, lambda _, __: self.shutdown())
+            signal.signal(signal.SIGTERM, lambda _, __: self.shutdown())

    def shutdown(self):
        # if this is our second call to shutdown, just sys.exit
@@ -225,7 +222,6 @@ class Node:
                            ),
                            local_event_sender=self.router.sender(topics.LOCAL_EVENTS),
                            event_index_counter=self.event_index_counter,
-                            offline=self.offline,
                        )
                        self._tg.start_soon(self.download_coordinator.run)
                    if self.worker:
@@ -264,9 +260,6 @@ def main():
    logger.info("Starting EXO")
    logger.info(f"EXO_LIBP2P_NAMESPACE: {os.getenv('EXO_LIBP2P_NAMESPACE')}")

-    if args.offline:
-        logger.info("Running in OFFLINE mode — no internet checks, local models only")
-
    # Set FAST_SYNCH override env var for runner subprocesses
    if args.fast_synch is True:
        os.environ["EXO_FAST_SYNCH"] = "on"
@@ -289,7 +282,6 @@ class Args(CamelCaseModel):
    tb_only: bool = False
    no_worker: bool = False
    no_downloads: bool = False
-    offline: bool = False
    fast_synch: bool | None = None  # None = auto, True = force on, False = force off

    @classmethod
@@ -337,11 +329,6 @@ class Args(CamelCaseModel):
            action="store_true",
            help="Disable the download coordinator (node won't download models)",
        )
-        parser.add_argument(
-            "--offline",
-            action="store_true",
-            help="Run in offline/air-gapped mode: skip internet checks, use only pre-staged local models",
-        )
        fast_synch_group = parser.add_mutually_exclusive_group()
        fast_synch_group.add_argument(
            "--fast-synch",
--- a/src/exo/master/api.py
+++ b/src/exo/master/api.py
@@ -85,7 +85,6 @@ from exo.shared.types.api import (
    ImageGenerationTaskParams,
    ImageListItem,
    ImageListResponse,
-    ImageSize,
    ModelList,
    ModelListModel,
    PlaceInstanceParams,
@@ -101,7 +100,6 @@ from exo.shared.types.api import (
    TraceRankStats,
    TraceResponse,
    TraceStatsResponse,
-    normalize_image_size,
 )
 from exo.shared.types.chunks import (
    ErrorChunk,
@@ -753,11 +751,9 @@ class API:
        When stream=True and partial_images > 0, returns a StreamingResponse
        with SSE-formatted events for partial and final images.
        """
+        payload.model = await self._validate_image_model(ModelId(payload.model))
        payload = payload.model_copy(
-            update={
-                "model": await self._validate_image_model(ModelId(payload.model)),
-                "advanced_params": _ensure_seed(payload.advanced_params),
-            }
+            update={"advanced_params": _ensure_seed(payload.advanced_params)}
        )

        command = ImageGeneration(
@@ -1013,13 +1009,12 @@ class API:
    async def bench_image_generations(
        self, request: Request, payload: BenchImageGenerationTaskParams
    ) -> BenchImageGenerationResponse:
+        payload.model = await self._validate_image_model(ModelId(payload.model))
+
+        payload.stream = False
+        payload.partial_images = 0
        payload = payload.model_copy(
-            update={
-                "model": await self._validate_image_model(ModelId(payload.model)),
-                "stream": False,
-                "partial_images": 0,
-                "advanced_params": _ensure_seed(payload.advanced_params),
-            }
+            update={"advanced_params": _ensure_seed(payload.advanced_params)}
        )

        command = ImageGeneration(
@@ -1040,7 +1035,7 @@ class API:
        prompt: str,
        model: ModelId,
        n: int,
-        size: ImageSize,
+        size: str,
        response_format: Literal["url", "b64_json"],
        input_fidelity: Literal["low", "high"],
        stream: bool,
@@ -1110,7 +1105,7 @@ class API:
        prompt: str = Form(...),
        model: str = Form(...),
        n: int = Form(1),
-        size: str | None = Form(None),
+        size: str = Form("1024x1024"),
        response_format: Literal["url", "b64_json"] = Form("b64_json"),
        input_fidelity: Literal["low", "high"] = Form("low"),
        stream: str = Form("false"),
@@ -1136,7 +1131,7 @@ class API:
            prompt=prompt,
            model=ModelId(model),
            n=n,
-            size=normalize_image_size(size),
+            size=size,
            response_format=response_format,
            input_fidelity=input_fidelity,
            stream=stream_bool,
@@ -1172,7 +1167,7 @@ class API:
        prompt: str = Form(...),
        model: str = Form(...),
        n: int = Form(1),
-        size: str | None = Form(None),
+        size: str = Form("1024x1024"),
        response_format: Literal["url", "b64_json"] = Form("b64_json"),
        input_fidelity: Literal["low", "high"] = Form("low"),
        quality: Literal["high", "medium", "low"] = Form("medium"),
@@ -1192,7 +1187,7 @@ class API:
            prompt=prompt,
            model=ModelId(model),
            n=n,
-            size=normalize_image_size(size),
+            size=size,
            response_format=response_format,
            input_fidelity=input_fidelity,
            stream=False,
@@ -1372,6 +1367,7 @@ class API:
    async def run(self):
        shutdown_ev = anyio.Event()

+        bonjour_cleanup = self._register_bonjour_service()
        try:
            async with create_task_group() as tg:
                self._tg = tg
@@ -1387,10 +1383,48 @@ class API:
                    with anyio.CancelScope(shield=True):
                        shutdown_ev.set()
        finally:
+            bonjour_cleanup()
            self._event_log.close()
            self.command_sender.close()
            self.global_event_receiver.close()

+    def _register_bonjour_service(self) -> Callable[[], None]:
+        """Register a Bonjour service via the system mDNSResponder. Returns a cleanup function."""
+        import subprocess
+        import sys
+
+        if sys.platform != "darwin":
+            logger.info("Bonjour service registration is only supported on macOS")
+            return lambda: None
+
+        service_name = f"EXO Cluster ({self.node_id[:8]})"
+        try:
+            proc = subprocess.Popen(
+                [
+                    "dns-sd",
+                    "-R",
+                    service_name,
+                    "_exo._tcp",
+                    "local",
+                    str(self.port),
+                    f"node_id={self.node_id}",
+                ],
+                stdout=subprocess.DEVNULL,
+                stderr=subprocess.DEVNULL,
+            )
+            logger.info(
+                f"Registered Bonjour service _exo._tcp on port {self.port} (pid {proc.pid})"
+            )
+
+            def cleanup() -> None:
+                proc.terminate()
+                proc.wait()
+
+            return cleanup
+        except Exception as e:
+            logger.warning(f"Failed to register Bonjour service: {e}")
+            return lambda: None
+
    async def run_api(self, ev: anyio.Event):
        cfg = Config()
        cfg.bind = [f"0.0.0.0:{self.port}"]
--- a/src/exo/shared/models/model_cards.py
+++ b/src/exo/shared/models/model_cards.py
@@ -44,8 +44,7 @@ async def _refresh_card_cache():
        async for toml_file in path.rglob("*.toml"):
            try:
                card = await ModelCard.load_from_path(toml_file)
-                if card.model_id not in _card_cache:
-                    _card_cache[card.model_id] = card
+                _card_cache[card.model_id] = card
            except (ValidationError, TOMLKitError):
                pass

@@ -183,7 +182,6 @@ class ConfigData(BaseModel):
    def supports_tensor(self) -> bool:
        return self.architectures in [
            ["Glm4MoeLiteForCausalLM"],
-            ["GlmMoeDsaForCausalLM"],
            ["DeepseekV32ForCausalLM"],
            ["DeepseekV3ForCausalLM"],
            ["Qwen3NextForCausalLM"],
--- a/src/exo/shared/types/api.py
+++ b/src/exo/shared/types/api.py
@@ -1,9 +1,9 @@
 import time
 from collections.abc import Generator
-from typing import Annotated, Any, Literal, get_args
+from typing import Annotated, Any, Literal
 from uuid import uuid4

-from pydantic import BaseModel, Field, field_validator
+from pydantic import BaseModel, Field

 from exo.shared.models.model_cards import ModelCard, ModelId
 from exo.shared.types.common import CommandId, NodeId
@@ -262,27 +262,6 @@ class DeleteInstanceResponse(BaseModel):
    instance_id: InstanceId


-ImageSize = Literal[
-    "auto",
-    "512x512",
-    "768x768",
-    "1024x768",
-    "768x1024",
-    "1024x1024",
-    "1024x1536",
-    "1536x1024",
-]
-
-
-def normalize_image_size(v: object) -> ImageSize:
-    """Shared validator for ImageSize fields: maps None → "auto" and rejects invalid values."""
-    if v is None:
-        return "auto"
-    if v not in get_args(ImageSize):
-        raise ValueError(f"Invalid size: {v!r}. Must be one of {get_args(ImageSize)}")
-    return v  # pyright: ignore[reportReturnType]
-
-
 class AdvancedImageParams(BaseModel):
    seed: Annotated[int, Field(ge=0)] | None = None
    num_inference_steps: Annotated[int, Field(ge=1, le=100)] | None = None
@@ -302,7 +281,7 @@ class ImageGenerationTaskParams(BaseModel):
    partial_images: int | None = 0
    quality: Literal["high", "medium", "low"] | None = "medium"
    response_format: Literal["url", "b64_json"] | None = "b64_json"
-    size: ImageSize = "auto"
+    size: str | None = "1024x1024"
    stream: bool | None = False
    style: str | None = "vivid"
    user: str | None = None
@@ -310,11 +289,6 @@ class ImageGenerationTaskParams(BaseModel):
    # Internal flag for benchmark mode - set by API, preserved through serialization
    bench: bool = False

-    @field_validator("size", mode="before")
-    @classmethod
-    def normalize_size(cls, v: object) -> ImageSize:
-        return normalize_image_size(v)
-

 class BenchImageGenerationTaskParams(ImageGenerationTaskParams):
    bench: bool = True
@@ -331,18 +305,13 @@ class ImageEditsTaskParams(BaseModel):
    quality: Literal["high", "medium", "low"] | None = "medium"
    output_format: Literal["png", "jpeg", "webp"] = "png"
    response_format: Literal["url", "b64_json"] | None = "b64_json"
-    size: ImageSize = "auto"
+    size: str | None = "1024x1024"
    image_strength: float | None = 0.7
    stream: bool = False
    partial_images: int | None = 0
    advanced_params: AdvancedImageParams | None = None
    bench: bool = False

-    @field_validator("size", mode="before")
-    @classmethod
-    def normalize_size(cls, v: object) -> ImageSize:
-        return normalize_image_size(v)
-
    def __repr_args__(self) -> Generator[tuple[str, Any], None, None]:
        for name, value in super().__repr_args__():  # pyright: ignore[reportAny]
            if name == "image_data":
--- a/src/exo/worker/engines/image/generate.py
+++ b/src/exo/worker/engines/image/generate.py
@@ -14,7 +14,6 @@ from exo.shared.types.api import (
    ImageEditsTaskParams,
    ImageGenerationStats,
    ImageGenerationTaskParams,
-    ImageSize,
 )
 from exo.shared.types.memory import Memory
 from exo.shared.types.worker.runner_response import (
@@ -24,9 +23,9 @@ from exo.shared.types.worker.runner_response import (
 from exo.worker.engines.image.distributed_model import DistributedImageModel


-def parse_size(size_str: ImageSize) -> tuple[int, int]:
+def parse_size(size_str: str | None) -> tuple[int, int]:
    """Parse size parameter like '1024x1024' to (width, height) tuple."""
-    if size_str == "auto":
+    if not size_str:
        return (1024, 1024)

    try:
@@ -110,9 +109,6 @@ def generate_image(
            # Decode base64 image data and save to temp file
            image_path = Path(tmpdir) / "input.png"
            image_path.write_bytes(base64.b64decode(task.image_data))
-            if task.size == "auto":
-                with Image.open(image_path) as img:
-                    width, height = img.size

        for image_num in range(num_images):
            # Increment seed for each image to ensure unique results
--- a/src/exo/worker/engines/mlx/auto_parallel.py
+++ b/src/exo/worker/engines/mlx/auto_parallel.py
@@ -163,14 +163,11 @@ class PipelineLastLayer(CustomMlxLayer):
                output, (self.r + 1) % self.s, group=self.group
            )
            if cache is not None:
-                # CacheList (used by MLA models like DeepSeekV32, GLM MoE DSA)
-                # doesn't have .keys directly; access via first sub-cache.
-                _cache = cache[0] if hasattr(cache, "caches") else cache  # type: ignore
-                _cache.keys = mx.depends(_cache.keys, output)  # type: ignore
+                cache.keys = mx.depends(cache.keys, output)  # type: ignore[reportUnknownMemberType]
            if self.is_prefill:
                mx.eval(output)
                if cache is not None:
-                    mx.eval(_cache.keys)  # type: ignore
+                    mx.eval(cache.keys)  # type: ignore

        if not self.is_prefill:
            output = mx.distributed.all_gather(output, group=self.group)[
@@ -310,9 +307,7 @@ def patch_pipeline_model[T](model: T, group: mx.distributed.Group) -> T:

        # Add dependency to last cache entry to ensure distributed ops are evaluated
        if cache is not None:
-            last = cache[-1]  # type: ignore
-            dep_cache = last[0] if hasattr(last, "caches") else last  # type: ignore
-            dep_cache.keys = mx.depends(dep_cache.keys, logits)  # type: ignore
+            cache[-1].state = mx.depends(cache[-1].state, logits)  # type: ignore

        return logits

@@ -338,9 +333,7 @@ def patch_tensor_model[T](model: T) -> T:

        # Add dependency to last cache entry to ensure distributed ops are evaluated
        if cache is not None and len(cache) > 0:  # pyright: ignore[reportAny]
-            last = cache[-1]  # pyright: ignore[reportAny]
-            dep_cache = last[0] if hasattr(last, "caches") else last  # pyright: ignore[reportAny]
-            dep_cache.keys = mx.depends(dep_cache.keys, logits)  # pyright: ignore[reportAny,reportUnknownMemberType]
+            cache[-1].state = mx.depends(cache[-1].state, logits)  # pyright: ignore[reportAny,reportUnknownMemberType]

        return logits

@@ -554,12 +547,10 @@ class DeepSeekShardingStrategy(TensorParallelShardingStrategy):
        on_timeout: TimeoutCallback | None,
    ) -> nn.Module:
        model = cast(DeepseekV3Model, model)
-
        for layer in model.layers:
            eval_with_timeout(
                layer.parameters(), timeout_seconds / len(model.layers), on_timeout
            )
-
            # Shard the self attention
            if layer.self_attn.q_lora_rank is None:
                layer.self_attn.q_proj = self.all_to_sharded_linear(
@@ -590,18 +581,12 @@ class DeepSeekShardingStrategy(TensorParallelShardingStrategy):
                layer.mlp.down_proj = self.sharded_to_all_linear(layer.mlp.down_proj)
                layer.mlp.up_proj = self.all_to_sharded_linear(layer.mlp.up_proj)

-            # Shard the MoE.
+            # Shard the MoE. Shard in place since the MoE should be responsible
+            # for aggregating the results.
            else:
-                if getattr(layer.mlp, "shared_experts", None) is not None:
-                    self.all_to_sharded_linear_in_place(
-                        layer.mlp.shared_experts.gate_proj
-                    )
-                    self.sharded_to_all_linear_in_place(
-                        layer.mlp.shared_experts.down_proj
-                    )
-                    self.all_to_sharded_linear_in_place(
-                        layer.mlp.shared_experts.up_proj
-                    )
+                self.all_to_sharded_linear_in_place(layer.mlp.shared_experts.gate_proj)
+                self.sharded_to_all_linear_in_place(layer.mlp.shared_experts.down_proj)
+                self.all_to_sharded_linear_in_place(layer.mlp.shared_experts.up_proj)
                self.all_to_sharded_linear_in_place(layer.mlp.switch_mlp.gate_proj)
                self.sharded_to_all_linear_in_place(layer.mlp.switch_mlp.down_proj)
                self.all_to_sharded_linear_in_place(layer.mlp.switch_mlp.up_proj)
@@ -794,7 +779,8 @@ class MiniMaxShardingStrategy(TensorParallelShardingStrategy):

            layer.self_attn = WrappedMiniMaxAttention(layer.self_attn, self.group)  # pyright: ignore[reportAttributeAccessIssue,reportArgumentType]

-            # Shard the MoE.
+            # Shard the MoE. Shard in place since the MoE should be responsible
+            # for aggregating the results.
            self.all_to_sharded_linear_in_place(
                layer.block_sparse_moe.switch_mlp.gate_proj
            )
@@ -907,7 +893,8 @@ class QwenShardingStrategy(TensorParallelShardingStrategy):
                    layer.self_attn.num_attention_heads //= self.N
                    layer.self_attn.num_key_value_heads //= self.N

-            # Shard the MoE.
+            # Shard the MoE. Shard in place since the MoE should be responsible
+            # for aggregating the results.
            if isinstance(layer.mlp, (Qwen3MoeSparseMoeBlock, Qwen3NextSparseMoeBlock)):
                self.all_to_sharded_linear_in_place(layer.mlp.switch_mlp.gate_proj)
                self.sharded_to_all_linear_in_place(layer.mlp.switch_mlp.down_proj)
--- a/src/exo/worker/engines/mlx/generator/generate.py
+++ b/src/exo/worker/engines/mlx/generator/generate.py
@@ -57,7 +57,6 @@ def prefill(
    sampler: Callable[[mx.array], mx.array],
    prompt_tokens: mx.array,
    cache: KVCacheType,
-    group: mx.distributed.Group | None = None,
 ) -> tuple[float, int, list[CacheSnapshot]]:
    """Prefill the KV cache with prompt tokens.

@@ -87,9 +86,6 @@ def prefill(

    set_pipeline_prefill(model, is_prefill=True)

-    mx_barrier(group)
-    logger.info("Starting prefill")
-
    # Use max_tokens=1 because max_tokens=0 does not work.
    # We just throw away the generated token - we only care about filling the cache
    for _ in stream_generate(
@@ -309,9 +305,16 @@ def mlx_generate(
    )
    max_stop_len = max((len(s) for s in stop_sequences), default=0)

+    mx_barrier(group)
+    logger.info("Starting prefill")
+
    # Prefill cache with all tokens except the last one
    prefill_tps, prefill_tokens, ssm_snapshots_list = prefill(
-        model, tokenizer, sampler, prompt_tokens[:-1], caches, group
+        model,
+        tokenizer,
+        sampler,
+        prompt_tokens[:-1],
+        caches,
    )
    cache_snapshots: list[CacheSnapshot] | None = ssm_snapshots_list or None

@@ -328,7 +331,6 @@ def mlx_generate(
    think_start = tokenizer.think_start
    think_end = tokenizer.think_end

-    logger.info("Starting decode")
    mx_barrier(group)

    for completion_tokens, out in enumerate(
--- a/src/exo/worker/engines/mlx/utils_mlx.py
+++ b/src/exo/worker/engines/mlx/utils_mlx.py
@@ -285,12 +285,10 @@ def get_eos_token_ids_for_model(model_id: ModelId) -> list[int] | None:
    model_id_lower = model_id.lower()
    if "kimi-k2" in model_id_lower:
        return [163586]
-    elif "glm-5" in model_id_lower or "glm-4.7" in model_id_lower:
-        # For GLM-5 and GLM-4.7
+    elif "glm-4.7-flash" in model_id_lower:
        # 154820: <|endoftext|>, 154827: <|user|>, 154829: <|observation|>
        return [154820, 154827, 154829]
    elif "glm" in model_id_lower:
-        # For GLM-4.5 and older
        return [151336, 151329, 151338]
    return None

--- a/src/exo/worker/runner/runner_supervisor.py
+++ b/src/exo/worker/runner/runner_supervisor.py
@@ -191,7 +191,7 @@ class RunnerSupervisor:
        logger.info("Checking runner's status")
        if self.runner_process.is_alive():
            logger.info("Runner was found to be alive, attempting to join process")
-            await to_thread.run_sync(self.runner_process.join, 5)
+            await to_thread.run_sync(self.runner_process.join, 1)
        rc = self.runner_process.exitcode
        logger.info(f"RunnerSupervisor exited with exit code {rc}")
        if rc == 0:
--- a/uv.lock
+++ b/uv.lock
@@ -377,8 +377,8 @@ dependencies = [
    { name = "hypercorn", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "loguru", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "mflux", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", version = "0.30.6", source = { registry = "https://pypi.org/simple" }, extra = ["cpu"], marker = "sys_platform == 'linux'" },
-    { name = "mlx", version = "0.30.7.dev20260218+14841977", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#1484197707f35186ad3bd614357c7c47fdf86ebc" }, marker = "sys_platform == 'darwin'" },
+    { name = "mlx", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "mlx", extra = ["cpu"], marker = "sys_platform == 'linux'" },
    { name = "mlx-lm", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "msgspec", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "openai-harmony", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -416,9 +416,9 @@ requires-dist = [
    { name = "hypercorn", specifier = ">=0.18.0" },
    { name = "loguru", specifier = ">=0.7.3" },
    { name = "mflux", specifier = "==0.15.5" },
-    { name = "mlx", marker = "sys_platform == 'darwin'", git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks" },
+    { name = "mlx", marker = "sys_platform == 'darwin'", specifier = "==0.30.6" },
    { name = "mlx", extras = ["cpu"], marker = "sys_platform == 'linux'", specifier = "==0.30.6" },
-    { name = "mlx-lm", specifier = "==0.30.7" },
+    { name = "mlx-lm", specifier = "==0.30.6" },
    { name = "msgspec", specifier = ">=0.19.0" },
    { name = "openai-harmony", specifier = ">=0.0.8" },
    { name = "pillow", specifier = ">=11.0,<12.0" },
@@ -1020,8 +1020,8 @@ dependencies = [
    { name = "fonttools", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "huggingface-hub", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "matplotlib", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", version = "0.30.6", source = { registry = "https://pypi.org/simple" }, extra = ["cuda13"], marker = "sys_platform == 'linux'" },
-    { name = "mlx", version = "0.30.7.dev20260218+14841977", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#1484197707f35186ad3bd614357c7c47fdf86ebc" }, marker = "sys_platform == 'darwin'" },
+    { name = "mlx", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "mlx", extra = ["cuda13"], marker = "sys_platform == 'linux'" },
    { name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "opencv-python", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "piexif", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -1048,12 +1048,18 @@ wheels = [
 name = "mlx"
 version = "0.30.6"
 source = { registry = "https://pypi.org/simple" }
-resolution-markers = [
-    "sys_platform == 'linux'",
+dependencies = [
+    { name = "mlx-metal", marker = "sys_platform == 'darwin'" },
 ]
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/ae/5b/e460e144a34d5529e010056cccf50b538d56ed001473bc6b246018fd58cb/mlx-0.30.6-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:ed86f8bffc174c2f259ca589ea25464c96cf69d1bb457074a2bf2ef53737e54f", size = 573515, upload-time = "2026-02-06T03:45:23.405Z" },
+    { url = "https://files.pythonhosted.org/packages/60/25/69833fefb9a3fef30b56792b1bcd022496c4fea83e45411d289b77ef7546/mlx-0.30.6-cp313-cp313-macosx_15_0_arm64.whl", hash = "sha256:c52294958269e20f300639a17c1900ca8fc737d859ddda737f9811e94bd040e5", size = 573516, upload-time = "2026-02-06T03:45:24.618Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/6a/7e7fbeebc5cb51b6a5eba96b263a6298707bcbdc059f4b0b73e088bc3dea/mlx-0.30.6-cp313-cp313-macosx_26_0_arm64.whl", hash = "sha256:b5b6636f7c49a4d86d8ec82643b972f45a144a7a9f3a967b27b2e6e22cf71e6a", size = 573592, upload-time = "2026-02-06T03:45:25.928Z" },
    { url = "https://files.pythonhosted.org/packages/93/06/280f6f2ba80520a7109730425eda0d966658793aa0d02d8be8d351f75253/mlx-0.30.6-cp313-cp313-manylinux_2_35_aarch64.whl", hash = "sha256:67e6c9e30a9faeacc209917ef5523177cf9b086914b6b5d83ff886e4294b727d", size = 622011, upload-time = "2026-02-06T03:45:28.165Z" },
    { url = "https://files.pythonhosted.org/packages/fe/35/f872afbee9c079cc69924d9e9c46f5663adb7da58cba3511db082dd307c1/mlx-0.30.6-cp313-cp313-manylinux_2_35_x86_64.whl", hash = "sha256:47db8b16fcb6f6c5a47c0bdb24ed377b41237017ac93aa6cb6aa206c9bdf82e4", size = 663650, upload-time = "2026-02-06T03:45:30.315Z" },
+    { url = "https://files.pythonhosted.org/packages/60/23/361dc7a5797634e4d7e9bdd6564c6b28f9b1246672632def2f91bf066b18/mlx-0.30.6-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:78804a89dcff4a838f7c2da72392fe87a523e95122a3c840e53df019122aad45", size = 575028, upload-time = "2026-02-06T03:45:31.549Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/69/1854484d414171586814dfbe8def95f75c4ea2c7341ba13ba8ee675f7c62/mlx-0.30.6-cp314-cp314-macosx_15_0_arm64.whl", hash = "sha256:ec13584ab069665cc7ad34a05494d9291cd623aef6ae96be48875fc87cfc25d6", size = 575026, upload-time = "2026-02-06T03:45:33.072Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/b8/3adbc441924209a7e4c568308b2a0b54bd09aee6a68db5bae85304791e54/mlx-0.30.6-cp314-cp314-macosx_26_0_arm64.whl", hash = "sha256:b2c5e8a090a753ef99a1380a4d059c983083f36198864f6df9faaf1223d083df", size = 575041, upload-time = "2026-02-06T03:45:34.814Z" },
    { url = "https://files.pythonhosted.org/packages/3f/54/9d9e06804fb2088202a2cdf60458e00b221f71420bea285720b60f9e82b5/mlx-0.30.6-cp314-cp314-manylinux_2_35_aarch64.whl", hash = "sha256:9ceddede4af0de31d1f6b3099f70e5469d60cd7c546975dedbdbeab3519cab3f", size = 624002, upload-time = "2026-02-06T03:45:36Z" },
    { url = "https://files.pythonhosted.org/packages/42/92/3140a15a50cb1f9267a6552171e1dfa577861de53e093124bc43707f2a0e/mlx-0.30.6-cp314-cp314-manylinux_2_35_x86_64.whl", hash = "sha256:4a6ffd2d16728cf95f63a1b555d7c2eaeea686a0e6b73228bd265411cb5d77a4", size = 663569, upload-time = "2026-02-06T03:45:37.242Z" },
 ]
@@ -1066,14 +1072,6 @@ cuda13 = [
    { name = "mlx-cuda-13", marker = "sys_platform == 'linux'" },
 ]

-[[package]]
-name = "mlx"
-version = "0.30.7.dev20260218+14841977"
-source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#1484197707f35186ad3bd614357c7c47fdf86ebc" }
-resolution-markers = [
-    "sys_platform == 'darwin'",
-]
-
 [[package]]
 name = "mlx-cpu"
 version = "0.30.6"
@@ -1100,20 +1098,30 @@ wheels = [

 [[package]]
 name = "mlx-lm"
-version = "0.30.7"
+version = "0.30.6"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "jinja2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", version = "0.30.7.dev20260218+14841977", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#1484197707f35186ad3bd614357c7c47fdf86ebc" }, marker = "sys_platform == 'darwin'" },
+    { name = "mlx", marker = "sys_platform == 'darwin'" },
    { name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "protobuf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "pyyaml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "sentencepiece", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "transformers", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/66/0d/56542e2ae13ec6f542d3977d7cff89a205d4f6c5122e0ce23f33265f61c9/mlx_lm-0.30.7.tar.gz", hash = "sha256:e5f31ac58d9f2381f28e1ba639ff903e64f7cff1bdc245c0bc97f72264be329c", size = 275764, upload-time = "2026-02-12T18:41:11.86Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/76/cb/815deddc8699b1f694d7e1f9cbed52934c03a8b49432c8add72932bb2f0b/mlx_lm-0.30.6.tar.gz", hash = "sha256:807e042d7040268f1b19190b7eaefd8b2efbff5590a65460974ad4225b91dda1", size = 271733, upload-time = "2026-02-04T21:27:45.741Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/1e/17/a41c798a3d9cbdc47f39c6db5bba4c2cd199203ead26bf911cb03b644070/mlx_lm-0.30.7-py3-none-any.whl", hash = "sha256:17442a4bf01c4c2d3bca1e647712fe44f19890c3f1eadc8589d389e57b44b9bf", size = 386591, upload-time = "2026-02-12T18:41:10.236Z" },
+    { url = "https://files.pythonhosted.org/packages/20/5f/01d281f1fa8a1521d5936659beb4f5ab1f32b463d059263cf9d4cef969d9/mlx_lm-0.30.6-py3-none-any.whl", hash = "sha256:a7405bd581eacc4bf8209d7a6b7f23629585a0d7c6740c2a97e51fee35b3b0e1", size = 379451, upload-time = "2026-02-04T21:27:43.222Z" },
+]
+
+[[package]]
+name = "mlx-metal"
+version = "0.30.6"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f3/85/44406b521f920248fad621334d4dc15e77660a494edf890e7cbee33bf38d/mlx_metal-0.30.6-py3-none-macosx_14_0_arm64.whl", hash = "sha256:ea6d0c973def9a5b4f652cc77036237db3f88c9d0af63701d76b5fddde99b820", size = 38437818, upload-time = "2026-02-06T03:44:56.19Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/cb/10a516995f7d0c154b0d7e633c54b51e96977a86a355105b6474cfcbe0d0/mlx_metal-0.30.6-py3-none-macosx_15_0_arm64.whl", hash = "sha256:0f8cb94634d07e06a372d6ad9a090f38a18bab1ff19a140aede60eacf707bb94", size = 38433701, upload-time = "2026-02-06T03:44:59.678Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/7d/70cb272f7373c334709f210ed8420511fc9d64d05a7a646c0b3b94c29c04/mlx_metal-0.30.6-py3-none-macosx_26_0_arm64.whl", hash = "sha256:d761ae26304f2c4b454eeea7f612a56919d9e5e57dbb1dc0788f8e34aa6f41c2", size = 47718448, upload-time = "2026-02-06T03:45:03.133Z" },
 ]

 [[package]]
Author	SHA1	Message	Date
Sami Khan	3e9eb93f82	exo theme	2026-02-19 04:21:58 +05:00
Sami Khan	ab622f79c3	EXO iOS app	2026-02-18 06:40:07 +05:00