chore(gallery): add GUI-Owl 1.5 2B variants

Add Q4_K_M and Q8_0 GGUF builds for screenshot interpretation and GUI
planning with llama.cpp. Include the F16 vision projector in both builds
and document installation and the separate action executor requirement.

Pin all downloads and verify SHA256 values against Hugging Face LFS
metadata and download headers.

Assisted-by: Codex:gpt-6

(cherry picked from commit c4273485d1, mudler/LocalAI#12541)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

gallery/index.yaml

@@ -23203,6 +23203,94 @@
     - filename: mmproj/mmproj-Qwen3-VL-2B-Thinking-F16.gguf
       sha256: 4eabc90a52fe890d6ca1dad92548782eab6edc91f012a365fff95cf027ba529d
       uri: huggingface://unsloth/Qwen3-VL-2B-Thinking-GGUF/mmproj-F16.gguf
+- name: gui-owl-1.5-2b-instruct
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  variants:
+    - model: gui-owl-1.5-2b-instruct-q8
+  urls:
+    - https://huggingface.co/mPLUG/GUI-Owl-1.5-2B-Instruct
+    - https://huggingface.co/mradermacher/GUI-Owl-1.5-2B-Instruct-GGUF
+  description: |
+    GUI-Owl 1.5 is a Qwen3-VL-based model for interpreting screenshots and
+    planning GUI actions across desktop, mobile, and browser interfaces.
+    This 2B Instruct Q4_K_M GGUF build includes the F16 vision projector
+    and uses the embedded chat template with a 32K-token default context.
+    A separate agent must execute the predicted actions.
+  license: mit
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - vision
+    - multimodal
+  last_checked: "2026-10-07"
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: GUI-Owl-1.5-2B-Instruct.mmproj-f16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: GUI-Owl-1.5-2B-Instruct.Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: GUI-Owl-1.5-2B-Instruct.Q4_K_M.gguf
+      uri: https://huggingface.co/mradermacher/GUI-Owl-1.5-2B-Instruct-GGUF/resolve/a0592aa615540e507a918bc6281fdbfc1b441361/GUI-Owl-1.5-2B-Instruct.Q4_K_M.gguf
+      sha256: 5fd2c77781a14a91128928b5bd313252aab076b44682396af4bb2c99667f5ef5
+    - filename: GUI-Owl-1.5-2B-Instruct.mmproj-f16.gguf
+      uri: https://huggingface.co/mradermacher/GUI-Owl-1.5-2B-Instruct-GGUF/resolve/a0592aa615540e507a918bc6281fdbfc1b441361/GUI-Owl-1.5-2B-Instruct.mmproj-f16.gguf
+      sha256: e3e3816edb92e62a51f8754b21f1369d8c0224f5488a878a4ef8284903bcf64a
+- name: gui-owl-1.5-2b-instruct-q8
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/mPLUG/GUI-Owl-1.5-2B-Instruct
+    - https://huggingface.co/mradermacher/GUI-Owl-1.5-2B-Instruct-GGUF
+  description: |
+    GUI-Owl 1.5 is a Qwen3-VL-based model for interpreting screenshots and
+    planning GUI actions across desktop, mobile, and browser interfaces.
+    This 2B Instruct Q8_0 GGUF build includes the F16 vision projector
+    and uses the embedded chat template with a 32K-token default context.
+    A separate agent must execute the predicted actions.
+  license: mit
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - vision
+    - multimodal
+  last_checked: "2026-10-07"
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    function:
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: GUI-Owl-1.5-2B-Instruct.mmproj-f16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: GUI-Owl-1.5-2B-Instruct.Q8_0.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: GUI-Owl-1.5-2B-Instruct.Q8_0.gguf
+      uri: https://huggingface.co/mradermacher/GUI-Owl-1.5-2B-Instruct-GGUF/resolve/a0592aa615540e507a918bc6281fdbfc1b441361/GUI-Owl-1.5-2B-Instruct.Q8_0.gguf
+      sha256: ed0901d94648da2e317dd577e3005914b8a721cb194dac1258557b214c19f5a4
+    - filename: GUI-Owl-1.5-2B-Instruct.mmproj-f16.gguf
+      uri: https://huggingface.co/mradermacher/GUI-Owl-1.5-2B-Instruct-GGUF/resolve/a0592aa615540e507a918bc6281fdbfc1b441361/GUI-Owl-1.5-2B-Instruct.mmproj-f16.gguf
+      sha256: e3e3816edb92e62a51f8754b21f1369d8c0224f5488a878a4ef8284903bcf64a
 - name: qwen3-vl-2b-instruct
   url: github:mudler/LocalAI/gallery/qwen3.yaml@master
   urls: