gallery: add KAT-Coder V2.5 Dev GGUF variants (#11186)

* gallery: add KAT-Coder V2.5 Dev GGUF variants Add Q4_K_M and Q8_0 builds of the newly released KAT-Coder-V2.5-Dev agentic coding model. Assisted-by: Codex:gpt-5 [Hugging Face API] * gallery: add KAT-Coder APEX variants Assisted-by: Codex:gpt-5 [web] * gallery: add KAT-Coder APEX checksums Assisted-by: Codex:gpt-5 --------- Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
2026-07-30 01:48:06 -04:00 · 2026-07-29 15:35:51 +02:00
parent 49ef40a187
commit 89ee62b2af
1 changed files with 226 additions and 0 deletions
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,230 @@
 ---
+- &kat-coder-v2-5-dev
+  name: "kat-coder-v2.5-dev"
+  variants:
+    - model: kat-coder-v2.5-dev-q8
+    - model: kat-coder-v2.5-dev-apex-i-quality
+    - model: kat-coder-v2.5-dev-apex-i-balanced
+    - model: kat-coder-v2.5-dev-apex-i-compact
+    - model: kat-coder-v2.5-dev-apex-i-mini
+    - model: kat-coder-v2.5-dev-apex-quality
+    - model: kat-coder-v2.5-dev-apex-balanced
+    - model: kat-coder-v2.5-dev-apex-compact
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/Kwaipilot/KAT-Coder-V2.5-Dev
+    - https://huggingface.co/bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF
+    - https://huggingface.co/mudler/KAT-Coder-V2.5-Dev-APEX-GGUF
+  description: |
+    KAT-Coder-V2.5-Dev is an Apache-2.0 agentic coding model from Kwaipilot,
+    post-trained from Qwen3.6-35B-A3B. It has 35 billion total parameters with
+    3 billion activated per token, a 262K-token context window, and text-only
+    weights tuned for repository-level coding and tool use.
+
+    This entry offers standard Q4_K_M and Q8_0 GGUF quantizations alongside
+    APEX mixed-precision variants with quality, balanced, compact, and mini
+    profiles. The APEX I-profiles use importance-matrix calibration.
+  license: "apache-2.0"
+  icon: https://huggingface.co/Kwaipilot/KAT-Coder-V2.5-Dev/resolve/main/kat_logo_hd.png
+  tags:
+    - llm
+    - gguf
+    - qwen
+    - coding
+  last_checked: "2026-07-29"
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF/Kwaipilot_KAT-Coder-V2.5-Dev-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF/Kwaipilot_KAT-Coder-V2.5-Dev-Q4_K_M.gguf
+      sha256: 4221c26e5663502d1c96fc901c9967d0e70ce2dcfaa5a9fb9280a46bd19e3c07
+      uri: huggingface://bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF/Kwaipilot_KAT-Coder-V2.5-Dev-Q4_K_M.gguf
+- !!merge <<: *kat-coder-v2-5-dev
+  name: "kat-coder-v2.5-dev-q8"
+  variants: []
+  description: |
+    KAT-Coder-V2.5-Dev is an Apache-2.0 agentic coding model from Kwaipilot,
+    post-trained from Qwen3.6-35B-A3B. It has 35 billion total parameters with
+    3 billion activated per token, a 262K-token context window, and text-only
+    weights tuned for repository-level coding and tool use.
+
+    This entry uses the higher-quality Q8_0 GGUF quantization.
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF/Kwaipilot_KAT-Coder-V2.5-Dev-Q8_0.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF/Kwaipilot_KAT-Coder-V2.5-Dev-Q8_0.gguf
+      sha256: 5fa510f44779b0e3d38a6678985f417a1c65e3000405ca5d6dcf7fd065e47a15
+      uri: huggingface://bartowski/Kwaipilot_KAT-Coder-V2.5-Dev-GGUF/Kwaipilot_KAT-Coder-V2.5-Dev-Q8_0.gguf
+- !!merge <<: *kat-coder-v2-5-dev
+  name: "kat-coder-v2.5-dev-apex-i-quality"
+  variants: []
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Quality.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Quality.gguf
+      sha256: e1cf7f33e13ee787a8557effee41eef5261b24696e283ef9d320830ba39f6784
+      uri: huggingface://mudler/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Quality.gguf
+- !!merge <<: *kat-coder-v2-5-dev
+  name: "kat-coder-v2.5-dev-apex-i-balanced"
+  variants: []
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Balanced.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Balanced.gguf
+      sha256: ee6e0ec15964c42ba91831d13e9709239f1b74da3dc49dd3edec4ad6aed8029f
+      uri: huggingface://mudler/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Balanced.gguf
+- !!merge <<: *kat-coder-v2-5-dev
+  name: "kat-coder-v2.5-dev-apex-i-compact"
+  variants: []
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Compact.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Compact.gguf
+      sha256: 5235ac39e7989d9fcf08078acfa755611d42a1f80060d226e4aba04a3595d0d8
+      uri: huggingface://mudler/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Compact.gguf
+- !!merge <<: *kat-coder-v2-5-dev
+  name: "kat-coder-v2.5-dev-apex-i-mini"
+  variants: []
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Mini.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Mini.gguf
+      sha256: 9d901bf1c44946840e15e6f73a66782f56ae2f1a41d6508995ddcd976e9af878
+      uri: huggingface://mudler/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-I-Mini.gguf
+- !!merge <<: *kat-coder-v2-5-dev
+  name: "kat-coder-v2.5-dev-apex-quality"
+  variants: []
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-Quality.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-Quality.gguf
+      sha256: 849737baf59183ed518d34f2460f0dcd86190953ccc3213072bdcb1d7f8d2882
+      uri: huggingface://mudler/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-Quality.gguf
+- !!merge <<: *kat-coder-v2-5-dev
+  name: "kat-coder-v2.5-dev-apex-balanced"
+  variants: []
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-Balanced.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-Balanced.gguf
+      sha256: 9a5d31b110a95bc085d9851c420dd7a1ffeaec7c9263073c8850d8fb81c4f8ba
+      uri: huggingface://mudler/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-Balanced.gguf
+- !!merge <<: *kat-coder-v2-5-dev
+  name: "kat-coder-v2.5-dev-apex-compact"
+  variants: []
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-Compact.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-Compact.gguf
+      sha256: 98dfee53102bbf01e67a768066543a707b40f365ff71e35132ac432c58ad99fd
+      uri: huggingface://mudler/KAT-Coder-V2.5-Dev-APEX-GGUF/KAT-Coder-V2.5-Dev-APEX-Compact.gguf
 - name: "inkling"
  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
  urls: