feat(gallery): add Ornith 1.5 35B variants (#11714)

Add the official Q4_K_M and Q8_0 GGUF builds with their shared BF16 vision projector.

Assisted-by: Codex:gpt-5

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>

gallery/index.yaml

@@ -597,6 +597,103 @@
     - filename: llama-cpp/mmproj/ornith-1.5-9b/mmproj-BF16.gguf
       uri: huggingface://ornith-ai/Ornith-1.5-9B-GGUF/mmproj-Ornith-1.5-9B-BF16.gguf
       sha256: 626f9f90627402a6bf4a999111d0fbd69b5fcca7aa8ba089d69e5f10e8858e1d
+- &ornith-1-5-35b-a3b
+  name: "ornith-1.5-35b-a3b-q4"
+  variants:
+    - model: ornith-1.5-35b-a3b-q8
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B
+    - https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B-GGUF
+  description: |
+    Ornith-1.5-35B-A3B is an MIT-licensed Qwen3.5 mixture-of-experts model
+    from Ornith AI for agentic coding, reasoning, repository-level software
+    tasks, and tool use. It activates about 3B parameters per token and
+    supports text and image input with a context window of 262K tokens.
+
+    This default entry uses the Q4_K_M GGUF and BF16 vision projector. A
+    higher-quality Q8_0 model is available as a variant.
+  license: "mit"
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - qwen
+    - moe
+    - reasoning
+    - thinking
+    - coding
+    - agent
+    - tools
+    - vision
+    - multimodal
+    - long-context
+  last_checked: "2026-08-25"
+  overrides:
+    backend: llama-cpp
+    context_size: 262144
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/ornith-1.5-35b-a3b/mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/ornith-1.5-35b-a3b/Ornith-1.5-35B-Q4_K_M.gguf
+      repeat_penalty: 1
+      temperature: 0.6
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/ornith-1.5-35b-a3b/Ornith-1.5-35B-Q4_K_M.gguf
+      uri: huggingface://ornith-ai/Ornith-1.5-35B-A3B-GGUF/Ornith-1.5-35B-Q4_K_M.gguf
+      sha256: 42739874cc2ccfdb8523b23fbe52e29b2a7555c8176737ca9ca0b5d59859d41f
+    - filename: llama-cpp/mmproj/ornith-1.5-35b-a3b/mmproj-BF16.gguf
+      uri: huggingface://ornith-ai/Ornith-1.5-35B-A3B-GGUF/mmproj-Ornith-1.5-35B-BF16.gguf
+      sha256: 1921a36a85aee56cd2abd27f46701802c9d85a33474792e600df6c3b282a135d
+- !!merge <<: *ornith-1-5-35b-a3b
+  name: "ornith-1.5-35b-a3b-q8"
+  variants: []
+  description: |
+    Ornith-1.5-35B-A3B in the higher-quality Q8_0 GGUF format, with the shared
+    BF16 vision projector for multimodal prompts.
+  overrides:
+    backend: llama-cpp
+    context_size: 262144
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/ornith-1.5-35b-a3b/mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/ornith-1.5-35b-a3b/Ornith-1.5-35B-Q8_0.gguf
+      repeat_penalty: 1
+      temperature: 0.6
+      top_k: 20
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/ornith-1.5-35b-a3b/Ornith-1.5-35B-Q8_0.gguf
+      uri: huggingface://ornith-ai/Ornith-1.5-35B-A3B-GGUF/Ornith-1.5-35B-Q8_0.gguf
+      sha256: de46c4baf4b4dd85ea438bb0f757f21c38841a353506579979bba114311658c3
+    - filename: llama-cpp/mmproj/ornith-1.5-35b-a3b/mmproj-BF16.gguf
+      uri: huggingface://ornith-ai/Ornith-1.5-35B-A3B-GGUF/mmproj-Ornith-1.5-35B-BF16.gguf
+      sha256: 1921a36a85aee56cd2abd27f46701802c9d85a33474792e600df6c3b282a135d
 - &qwen3-8-27b-obliterated
   name: "qwen3.8-27b-obliterated-q4"
   variants: