EXO iOS app

2026-02-18 14:55:13 -05:00 · 2026-02-18 06:40:07 +05:00
39 changed files with 2620 additions and 154 deletions
--- 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 +1,11 @@
+{
+  "colors" : [
+    {
+      "idiom" : "universal"
+    }
+  ],
+  "info" : {
+    "author" : "xcode",
+    "version" : 1
+  }
+}
--- 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 +1,35 @@
+{
+  "images" : [
+    {
+      "idiom" : "universal",
+      "platform" : "ios",
+      "size" : "1024x1024"
+    },
+    {
+      "appearances" : [
+        {
+          "appearance" : "luminosity",
+          "value" : "dark"
+        }
+      ],
+      "idiom" : "universal",
+      "platform" : "ios",
+      "size" : "1024x1024"
+    },
+    {
+      "appearances" : [
+        {
+          "appearance" : "luminosity",
+          "value" : "tinted"
+        }
+      ],
+      "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/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 +1,42 @@
+import SwiftUI
+
+@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?
+
+    var body: some Scene {
+        WindowGroup {
+            if let chatService {
+                RootView()
+                    .environment(clusterService)
+                    .environment(discoveryService)
+                    .environment(chatService)
+                    .environment(localInferenceService)
+                    .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.clear.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 +1,17 @@
+<?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>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 +1,225 @@
+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 +1,198 @@
+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 +1,118 @@
+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 +1,171 @@
+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
+
+            Divider()
+
+            messageList
+
+            Divider()
+
+            inputBar
+        }
+        .sheet(isPresented: $showModelSelector) {
+            ModelSelectorView(
+                models: clusterService.availableModels,
+                selectedModelId: chatService.activeConversation?.modelId
+            ) { modelId in
+                chatService.setModelForActiveConversation(modelId)
+            }
+        }
+    }
+
+    // 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")
+                    .foregroundStyle(useLocalModel ? .blue : .secondary)
+
+                if useLocalModel {
+                    Text(localInferenceService.defaultModelId)
+                        .font(.subheadline)
+                        .lineLimit(1)
+                } else if let modelId = chatService.activeConversation?.modelId {
+                    Text(modelId)
+                        .font(.subheadline)
+                        .lineLimit(1)
+                } else {
+                    Text("Select Model")
+                        .font(.subheadline)
+                        .foregroundStyle(.secondary)
+                }
+
+                Spacer()
+
+                if useLocalModel {
+                    Text("On-Device")
+                        .font(.caption2)
+                        .foregroundStyle(.blue)
+                        .padding(.horizontal, 6)
+                        .padding(.vertical, 2)
+                        .background(.blue.opacity(0.1))
+                        .clipShape(Capsule())
+                } else {
+                    Image(systemName: "chevron.right")
+                        .font(.caption)
+                        .foregroundStyle(.tertiary)
+                }
+            }
+            .padding(.horizontal)
+            .padding(.vertical, 10)
+            .background(Color(.secondarySystemBackground))
+        }
+        .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()
+            }
+            .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: 12) {
+            Spacer(minLength: 80)
+            Image(systemName: "bubble.left.and.bubble.right")
+                .font(.system(size: 48))
+                .foregroundStyle(.tertiary)
+            Text("Start a conversation")
+                .font(.headline)
+                .foregroundStyle(.secondary)
+            Text("Send a message to begin chatting with the model.")
+                .font(.subheadline)
+                .foregroundStyle(.tertiary)
+                .multilineTextAlignment(.center)
+            Spacer(minLength: 80)
+        }
+        .padding()
+    }
+
+    // MARK: - Input
+
+    private var inputBar: some View {
+        HStack(alignment: .bottom, spacing: 8) {
+            TextField("Message...", text: $inputText, axis: .vertical)
+                .lineLimit(1...6)
+                .textFieldStyle(.plain)
+                .padding(10)
+                .background(Color(.tertiarySystemBackground))
+                .clipShape(RoundedRectangle(cornerRadius: 20))
+
+            if chatService.isGenerating {
+                Button {
+                    chatService.cancelGeneration()
+                } label: {
+                    Image(systemName: "stop.circle.fill")
+                        .font(.title2)
+                        .foregroundStyle(.red)
+                }
+            } else {
+                Button {
+                    let text = inputText
+                    inputText = ""
+                    chatService.sendMessage(text)
+                } label: {
+                    Image(systemName: "arrow.up.circle.fill")
+                        .font(.title2)
+                        .foregroundStyle(canSend ? Color.accentColor : Color.gray)
+                }
+                .disabled(!canSend)
+            }
+        }
+        .padding(.horizontal)
+        .padding(.vertical, 8)
+    }
+
+    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 +1,27 @@
+import SwiftUI
+
+struct MessageBubbleView: View {
+    let message: ChatMessage
+
+    var body: some View {
+        HStack {
+            if message.role == .user { Spacer(minLength: 48) }
+
+            VStack(alignment: message.role == .user ? .trailing : .leading, spacing: 4) {
+                Text(message.content + (message.isStreaming ? " \u{258C}" : ""))
+                    .textSelection(.enabled)
+                    .padding(.horizontal, 14)
+                    .padding(.vertical, 10)
+                    .background(bubbleBackground)
+                    .foregroundStyle(message.role == .user ? .white : .primary)
+                    .clipShape(RoundedRectangle(cornerRadius: 16))
+            }
+
+            if message.role == .assistant { Spacer(minLength: 48) }
+        }
+    }
+
+    private var bubbleBackground: Color {
+        message.role == .user ? .accentColor : Color(.secondarySystemBackground)
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/Chat/ModelSelectorView.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/Chat/ModelSelectorView.swift
@@ -0,0 +1,66 @@
+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
+                }
+            }
+            .navigationTitle("Select Model")
+            .navigationBarTitleDisplayMode(.inline)
+            .toolbar {
+                ToolbarItem(placement: .cancellationAction) {
+                    Button("Cancel") { dismiss() }
+                }
+            }
+        }
+    }
+
+    private var emptyContent: some View {
+        ContentUnavailableView(
+            "No Models Available",
+            systemImage: "cpu",
+            description: Text("Connect to an EXO cluster to see available models.")
+        )
+    }
+
+    private var modelsList: some View {
+        ForEach(models) { model in
+            Button {
+                onSelect(model.id)
+                dismiss()
+            } label: {
+                modelRow(model)
+            }
+            .tint(.primary)
+        }
+    }
+
+    private func modelRow(_ model: ModelOption) -> some View {
+        HStack {
+            VStack(alignment: .leading, spacing: 2) {
+                Text(model.displayName)
+                    .fontWeight(.medium)
+                Text(model.id)
+                    .font(.caption)
+                    .foregroundStyle(.secondary)
+            }
+
+            Spacer()
+
+            if model.id == selectedModelId {
+                Image(systemName: "checkmark")
+                    .foregroundStyle(Color.accentColor)
+            }
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/Components/ConnectionStatusBadge.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/Components/ConnectionStatusBadge.swift
@@ -0,0 +1,62 @@
+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)
+
+            Text(label)
+                .font(.caption)
+                .fontWeight(.medium)
+        }
+        .padding(.horizontal, 10)
+        .padding(.vertical, 5)
+        .background(backgroundColor)
+        .clipShape(Capsule())
+    }
+
+    private var dotColor: Color {
+        if isLocalReady {
+            return .blue
+        }
+        switch connectionState {
+        case .connected: return .green
+        case .connecting: return .orange
+        case .disconnected: return .gray
+        }
+    }
+
+    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 .blue.opacity(0.15)
+        }
+        switch connectionState {
+        case .connected: return .green.opacity(0.15)
+        case .connecting: return .orange.opacity(0.15)
+        case .disconnected: return .gray.opacity(0.15)
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/RootView.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/RootView.swift
@@ -0,0 +1,117 @@
+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")
+                        }
+                    }
+                }
+        }
+        .sheet(isPresented: $showSettings) {
+            SettingsView()
+                .environment(discoveryService)
+        }
+        .sheet(isPresented: $showConversations) {
+            conversationList
+        }
+    }
+
+    // MARK: - Conversations
+
+    private var conversationMenuButton: some View {
+        HStack(spacing: 12) {
+            Button {
+                showConversations = true
+            } label: {
+                Image(systemName: "sidebar.left")
+            }
+
+            Button {
+                chatService.createConversation()
+            } label: {
+                Image(systemName: "square.and.pencil")
+            }
+        }
+    }
+
+    private var conversationList: some View {
+        NavigationStack {
+            List {
+                if chatService.conversations.isEmpty {
+                    Text("No conversations yet")
+                        .foregroundStyle(.secondary)
+                } else {
+                    ForEach(chatService.conversations) { conversation in
+                        Button {
+                            chatService.setActiveConversation(id: conversation.id)
+                            showConversations = false
+                        } label: {
+                            VStack(alignment: .leading, spacing: 4) {
+                                Text(conversation.title)
+                                    .fontWeight(
+                                        conversation.id == chatService.activeConversationId
+                                            ? .semibold : .regular
+                                    )
+                                    .lineLimit(1)
+
+                                if let modelId = conversation.modelId {
+                                    Text(modelId)
+                                        .font(.caption)
+                                        .foregroundStyle(.secondary)
+                                        .lineLimit(1)
+                                }
+                            }
+                        }
+                        .tint(.primary)
+                    }
+                    .onDelete { indexSet in
+                        for index in indexSet {
+                            chatService.deleteConversation(id: chatService.conversations[index].id)
+                        }
+                    }
+                }
+            }
+            .navigationTitle("Conversations")
+            .navigationBarTitleDisplayMode(.inline)
+            .toolbar {
+                ToolbarItem(placement: .confirmationAction) {
+                    Button("Done") { showConversations = false }
+                }
+                ToolbarItem(placement: .topBarLeading) {
+                    Button {
+                        chatService.createConversation()
+                    } label: {
+                        Image(systemName: "plus")
+                    }
+                }
+            }
+        }
+    }
+}
--- a/app/EXO-iOS/EXO-iOS/Views/Settings/SettingsView.swift
+++ b/app/EXO-iOS/EXO-iOS/Views/Settings/SettingsView.swift
@@ -0,0 +1,197 @@
+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
+            }
+            .navigationTitle("Settings")
+            .navigationBarTitleDisplayMode(.inline)
+            .toolbar {
+                ToolbarItem(placement: .confirmationAction) {
+                    Button("Done") { dismiss() }
+                }
+            }
+        }
+    }
+
+    private var localModelSection: some View {
+        Section {
+            HStack {
+                VStack(alignment: .leading, spacing: 4) {
+                    Text(localInferenceService.defaultModelId)
+                        .font(.subheadline)
+                        .fontWeight(.medium)
+
+                    Text(localModelStatusText)
+                        .font(.caption)
+                        .foregroundStyle(.secondary)
+                }
+
+                Spacer()
+
+                localModelActionButton
+            }
+
+            if case .downloading(let progress) = localInferenceService.modelState {
+                ProgressView(value: progress)
+                    .tint(.blue)
+            }
+        } header: {
+            Text("Local Model")
+        } footer: {
+            Text("When disconnected from a cluster, messages are processed on-device using this model.")
+        }
+    }
+
+    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:
+            Button("Download") {
+                Task { await localInferenceService.prepareModel() }
+            }
+            .buttonStyle(.borderedProminent)
+            .controlSize(.small)
+        case .downloading:
+            ProgressView()
+                .controlSize(.small)
+        case .downloaded:
+            Button("Load") {
+                Task { await localInferenceService.prepareModel() }
+            }
+            .buttonStyle(.bordered)
+            .controlSize(.small)
+        case .loading:
+            ProgressView()
+                .controlSize(.small)
+        case .ready, .generating:
+            Button("Unload") {
+                localInferenceService.unloadModel()
+            }
+            .buttonStyle(.bordered)
+            .controlSize(.small)
+        case .error:
+            Button("Retry") {
+                Task { await localInferenceService.prepareModel() }
+            }
+            .buttonStyle(.borderedProminent)
+            .controlSize(.small)
+            .tint(.red)
+        }
+    }
+
+    private var nearbyClustersSection: some View {
+        Section {
+            if discoveryService.discoveredClusters.isEmpty {
+                if discoveryService.isSearching {
+                    HStack {
+                        ProgressView()
+                            .padding(.trailing, 8)
+                        Text("Searching for clusters...")
+                            .foregroundStyle(.secondary)
+                    }
+                } else {
+                    Text("No clusters found")
+                        .foregroundStyle(.secondary)
+                }
+            } else {
+                ForEach(discoveryService.discoveredClusters) { cluster in
+                    HStack {
+                        VStack(alignment: .leading) {
+                            Text(cluster.name)
+                                .font(.body)
+                        }
+                        Spacer()
+                        Button("Connect") {
+                            Task {
+                                await clusterService.connectToDiscoveredCluster(
+                                    cluster, using: discoveryService
+                                )
+                                if clusterService.isConnected {
+                                    dismiss()
+                                }
+                            }
+                        }
+                        .buttonStyle(.borderedProminent)
+                        .controlSize(.small)
+                    }
+                }
+            }
+        } header: {
+            Text("Nearby Clusters")
+        }
+    }
+
+    private var connectionSection: some View {
+        Section("Manual Connection") {
+            TextField("IP Address (e.g. 192.168.1.42)", text: $host)
+                .keyboardType(.decimalPad)
+                .textContentType(.URL)
+                .autocorrectionDisabled()
+
+            TextField("Port", text: $port)
+                .keyboardType(.numberPad)
+
+            Button(clusterService.isConnected ? "Reconnect" : "Connect") {
+                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()
+                    }
+                }
+            }
+            .disabled(host.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty)
+        }
+    }
+
+    private var statusSection: some View {
+        Section("Status") {
+            if let connection = clusterService.currentConnection {
+                LabeledContent("Host", value: connection.host)
+                LabeledContent("Port", value: "\(connection.port)")
+                if let nodeId = connection.nodeId {
+                    LabeledContent("Node ID", value: String(nodeId.prefix(12)) + "...")
+                }
+                LabeledContent("Models", value: "\(clusterService.availableModels.count)")
+
+                Button("Disconnect", role: .destructive) {
+                    clusterService.disconnect()
+                }
+            } else {
+                if let error = clusterService.lastError {
+                    Label(error, systemImage: "exclamationmark.triangle")
+                        .foregroundStyle(.red)
+                } else {
+                    Text("Not connected")
+                        .foregroundStyle(.secondary)
+                }
+            }
+        }
+    }
+}
--- 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/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.dev20260217+50487b41"; 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 = "50487b4141f3c951122655db3b83df5146c1fbeb";
-      hash = "sha256-IL4a9vMX5nocgJU1WG4zE8hArHkHJtnh4sdYh3od5zU=";
+      owner = "ml-explore";
+      repo = "mlx";
+      tag = "v${version}";
+      hash = "sha256-avD5EGhwgmPdXLAyQSqTO6AXk/W3ziH+f6AetjK3Sdo=";
    };

    patches = [
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -17,7 +17,7 @@ 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==0.30.6",
    "tiktoken>=0.12.0", # required for kimi k2 tokenizer
@@ -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/src/exo/main.py
+++ b/src/exo/main.py
@@ -94,7 +94,6 @@ class Node:
                command_sender=router.sender(topics.COMMANDS),
                download_command_sender=router.sender(topics.DOWNLOAD_COMMANDS),
                event_index_counter=event_index_counter,
-                no_downloads=args.no_downloads,
            )
        else:
            worker = None
@@ -137,8 +136,6 @@ class Node:

    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:
@@ -150,6 +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
@@ -226,7 +225,6 @@ class Node:
                        )
                        self._tg.start_soon(self.download_coordinator.run)
                    if self.worker:
-                        no_downloads = self.worker.no_downloads
                        self.worker.shutdown()
                        # TODO: add profiling etc to resource monitor
                        self.worker = Worker(
@@ -241,7 +239,6 @@ class Node:
                                topics.DOWNLOAD_COMMANDS
                            ),
                            event_index_counter=self.event_index_counter,
-                            no_downloads=no_downloads,
                        )
                        self._tg.start_soon(self.worker.run)
                    if self.api:
--- a/src/exo/master/api.py
+++ b/src/exo/master/api.py
@@ -1367,6 +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
@@ -1382,10 +1383,38 @@ 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/worker/main.py
+++ b/src/exo/worker/main.py
@@ -65,7 +65,6 @@ class Worker:
        command_sender: Sender[ForwarderCommand],
        download_command_sender: Sender[ForwarderDownloadCommand],
        event_index_counter: Iterator[int],
-        no_downloads: bool = False,
    ):
        self.node_id: NodeId = node_id
        self.session_id: SessionId = session_id
@@ -75,7 +74,6 @@ class Worker:
        self.event_index_counter = event_index_counter
        self.command_sender = command_sender
        self.download_command_sender = download_command_sender
-        self.no_downloads = no_downloads
        self.event_buffer = OrderedBuffer[Event]()
        self.out_for_delivery: dict[EventId, ForwarderEvent] = {}

@@ -184,7 +182,6 @@ class Worker:
                self.state.tasks,
                self.input_chunk_buffer,
                self.input_chunk_counts,
-                no_downloads=self.no_downloads,
            )
            if task is None:
                continue
--- a/src/exo/worker/plan.py
+++ b/src/exo/worker/plan.py
@@ -51,20 +51,15 @@ def plan(
    tasks: Mapping[TaskId, Task],
    input_chunk_buffer: Mapping[CommandId, dict[int, str]] | None = None,
    input_chunk_counts: Mapping[CommandId, int] | None = None,
-    no_downloads: bool = False,
 ) -> Task | None:
    # Python short circuiting OR logic should evaluate these sequentially.
    return (
        _cancel_tasks(runners, tasks)
        or _kill_runner(runners, all_runners, instances)
        or _create_runner(node_id, runners, instances)
-        or (
-            None
-            if no_downloads
-            else _model_needs_download(node_id, runners, global_download_status)
-        )
+        or _model_needs_download(node_id, runners, global_download_status)
        or _init_distributed_backend(runners, all_runners)
-        or _load_model(runners, all_runners, global_download_status, no_downloads)
+        or _load_model(runners, all_runners, global_download_status)
        or _ready_to_warmup(runners, all_runners)
        or _pending_tasks(runners, tasks, all_runners, input_chunk_buffer or {})
    )
@@ -197,25 +192,22 @@ def _load_model(
    runners: Mapping[RunnerId, RunnerSupervisor],
    all_runners: Mapping[RunnerId, RunnerStatus],
    global_download_status: Mapping[NodeId, Sequence[DownloadProgress]],
-    no_downloads: bool = False,
 ) -> LoadModel | None:
    for runner in runners.values():
        instance = runner.bound_instance.instance
        shard_assignments = instance.shard_assignments

-        if not no_downloads:
-            all_local_downloads_complete = all(
-                nid in global_download_status
-                and any(
-                    isinstance(dp, DownloadCompleted)
-                    and dp.shard_metadata.model_card.model_id
-                    == shard_assignments.model_id
-                    for dp in global_download_status[nid]
-                )
-                for nid in shard_assignments.node_to_runner
+        all_local_downloads_complete = all(
+            nid in global_download_status
+            and any(
+                isinstance(dp, DownloadCompleted)
+                and dp.shard_metadata.model_card.model_id == shard_assignments.model_id
+                for dp in global_download_status[nid]
            )
-            if not all_local_downloads_complete:
-                continue
+            for nid in shard_assignments.node_to_runner
+        )
+        if not all_local_downloads_complete:
+            continue

        is_single_node_instance = len(instance.shard_assignments.runner_to_shard) == 1
        if is_single_node_instance and isinstance(runner.status, RunnerIdle):
--- a/src/exo/worker/tests/unittests/test_plan/test_download_and_loading.py
+++ b/src/exo/worker/tests/unittests/test_plan/test_download_and_loading.py
@@ -157,41 +157,6 @@ def test_plan_does_not_request_download_when_shard_already_downloaded():
    assert not isinstance(result, plan_mod.DownloadModel)


-def test_plan_loads_model_with_no_downloads_flag():
-    """
-    When no_downloads=True, plan() should skip download checks and proceed
-    to load the model even with empty global_download_status.
-    """
-    shard = get_pipeline_shard_metadata(model_id=MODEL_A_ID, device_rank=0)
-    instance = get_mlx_ring_instance(
-        instance_id=INSTANCE_1_ID,
-        model_id=MODEL_A_ID,
-        node_to_runner={NODE_A: RUNNER_1_ID},
-        runner_to_shard={RUNNER_1_ID: shard},
-    )
-    bound_instance = BoundInstance(
-        instance=instance, bound_runner_id=RUNNER_1_ID, bound_node_id=NODE_A
-    )
-    runner = FakeRunnerSupervisor(bound_instance=bound_instance, status=RunnerIdle())
-
-    runners = {RUNNER_1_ID: runner}
-    instances = {INSTANCE_1_ID: instance}
-    all_runners = {RUNNER_1_ID: RunnerIdle()}
-
-    result = plan_mod.plan(
-        node_id=NODE_A,
-        runners=runners,  # type: ignore
-        global_download_status={},
-        instances=instances,
-        all_runners=all_runners,
-        tasks={},
-        no_downloads=True,
-    )
-
-    assert isinstance(result, LoadModel)
-    assert result.instance_id == INSTANCE_1_ID
-
-
 def test_plan_does_not_load_model_until_all_shards_downloaded_globally():
    """
    LoadModel should not be emitted while some shards are still missing from
--- 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.dev20260217+50487b41", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#50487b4141f3c951122655db3b83df5146c1fbeb" }, 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'" },
@@ -416,7 +416,7 @@ 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 = "==0.30.6" },
    { name = "msgspec", specifier = ">=0.19.0" },
@@ -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.dev20260217+50487b41", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#50487b4141f3c951122655db3b83df5146c1fbeb" }, 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.dev20260217+50487b41"
-source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#50487b4141f3c951122655db3b83df5146c1fbeb" }
-resolution-markers = [
-    "sys_platform == 'darwin'",
-]
-
 [[package]]
 name = "mlx-cpu"
 version = "0.30.6"
@@ -1104,7 +1102,7 @@ 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.dev20260217+50487b41", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#50487b4141f3c951122655db3b83df5146c1fbeb" }, 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'" },
@@ -1116,6 +1114,16 @@ wheels = [
    { 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]]
 name = "more-itertools"
 version = "10.8.0"