gallery: add Fara1.5 9B GGUF variants (#11271)

Add the new 9B Fara computer-use model alongside its existing 27B sibling, with Q4_K_M and Q8_0 llama.cpp variants plus the required vision projector.

Assisted-by: Codex:gpt-5 [web]

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

Author: localai-org-maint-bot

gallery/index.yaml

@@ -5306,6 +5306,82 @@
     - filename: llama-cpp/models/Qwen3.5-35B-A3B-APEX-GGUF/Qwen3.5-35B-A3B-APEX-Quality.gguf
       sha256: 50887b60c77ee5c95bc3657814ae993abcab7b2d71868b9af1e84d6badd09a57
       uri: https://huggingface.co/mudler/Qwen3.5-35B-A3B-APEX-GGUF/resolve/main/Qwen3.5-35B-A3B-APEX-Quality.gguf
+- &fara1-5-9b
+  name: fara1.5-9b
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  variants:
+    - model: fara1.5-9b-q8
+  urls:
+    - https://huggingface.co/microsoft/Fara1.5-9B
+    - https://huggingface.co/bartowski/Fara1.5-9B-GGUF
+  description: |
+    Fara1.5-9B is Microsoft's 9B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-9B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the recommended Q4_K_M GGUF quantization.
+  license: mit
+  tags:
+    - fara
+    - qwen
+    - qwen3.5
+    - 9b
+    - llm
+    - gguf
+    - quantized
+    - chat
+    - vision
+    - multimodal
+    - agent
+    - computer-use
+    - gpu
+    - cpu
+  last_checked: "2026-08-01"
+  overrides:
+    backend: llama-cpp
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Fara1.5-9B-GGUF/Fara1.5-9B-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Fara1.5-9B-GGUF/Fara1.5-9B-Q4_K_M.gguf
+      sha256: a02e7220337b87290bca7ef7225ba4afa7104efa05c0851de6c29ec9c5d04c7d
+      uri: huggingface://bartowski/Fara1.5-9B-GGUF/Fara1.5-9B-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+      sha256: 97b423c81719ffc367124a9739d6feb6f62d62f60869a6d385a701b963ce1906
+      uri: huggingface://bartowski/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+- !!merge <<: *fara1-5-9b
+  name: fara1.5-9b-q8
+  variants: []
+  description: |
+    Fara1.5-9B is Microsoft's 9B-parameter multimodal computer-use agent for web browsers, fine-tuned from Qwen3.5-9B. It accepts screenshots and text, emits structured browser actions, supports a 262K-token context, and should be deployed with appropriate sandboxing and user-confirmation controls. This entry uses the higher-quality Q8_0 GGUF quantization.
+  overrides:
+    backend: llama-cpp
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/Fara1.5-9B-GGUF/Fara1.5-9B-Q8_0.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Fara1.5-9B-GGUF/Fara1.5-9B-Q8_0.gguf
+      sha256: a2e30cca7aec006266308153ae781347505af16baa514bbd4e0e3f4a79ea3a22
+      uri: huggingface://bartowski/Fara1.5-9B-GGUF/Fara1.5-9B-Q8_0.gguf
+    - filename: llama-cpp/mmproj/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
+      sha256: 97b423c81719ffc367124a9739d6feb6f62d62f60869a6d385a701b963ce1906
+      uri: huggingface://bartowski/Fara1.5-9B-GGUF/mmproj-Fara1.5-9B-f16.gguf
 - name: fara1.5-27b
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   variants: