gallery: consolidate POCKET-35B variants (#11249)

Keep the canonical POCKET-35B family, add its missing Q3_K_M build, and remove the duplicate artifact entries introduced by overlapping gallery additions.

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

@@ -2,6 +2,7 @@
 - &pocket-35b
   name: "pocket-35b"
   variants:
+    - model: pocket-35b-q3
     - model: pocket-35b-q2
     - model: pocket-35b-iq1
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
@@ -38,6 +39,31 @@
     - filename: llama-cpp/models/FINAL-Bench/POCKET-35B-GGUF/POCKET-35B-Q4_K_M.gguf
       sha256: 6f479f637c8fb932df39b9cfabdc454568eee48c0e7c0584e1815a27558e8ffe
       uri: huggingface://FINAL-Bench/POCKET-35B-GGUF/POCKET-35B-Q4_K_M.gguf
+- !!merge <<: *pocket-35b
+  name: "pocket-35b-q3"
+  variants: []
+  description: |
+    POCKET-35B is an Apache-2.0 Qwen3.5-family mixture-of-experts model from
+    FINAL-Bench/VIDRAFT, derived from Darwin-36B-Opus and packaged for stock
+    llama.cpp. This entry uses the balanced Q3_K_M 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/FINAL-Bench/POCKET-35B-GGUF/POCKET-35B-Q3_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/FINAL-Bench/POCKET-35B-GGUF/POCKET-35B-Q3_K_M.gguf
+      sha256: 9ab4184f0f5af0cc1cf8eee7e553664b692c3f837a8868c4a16137bb3a3c97a2
+      uri: huggingface://FINAL-Bench/POCKET-35B-GGUF/POCKET-35B-Q3_K_M.gguf
 - !!merge <<: *pocket-35b
   name: "pocket-35b-q2"
   variants: []
@@ -4988,97 +5014,6 @@
     - filename: mmproj-F16.gguf
       sha256: 6edcca228213c28d3567a35d22f849eea52d8360875093851959adf5d2f270eb
       uri: https://huggingface.co/unsloth/gemma-4-31B-it-GGUF/resolve/main/mmproj-F16.gguf
-- &pocket-35b
-  name: pocket-35b-q4-k-m
-  url: github:mudler/LocalAI/gallery/virtual.yaml@master
-  urls:
-    - https://huggingface.co/FINAL-Bench/Darwin-36B-Opus
-    - https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF
-  description: |
-    POCKET-35B is an Apache-2.0 Qwen3.5-family sparse MoE model derived from
-    Darwin-36B-Opus. Its official GGUF ladder spans Q4_K_M, Q3_K_M, Q2_K, and
-    IQ1_M so LocalAI can select a build for the available memory. All builds run
-    with the stock llama.cpp backend.
-  license: apache-2.0
-  icon: https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF/resolve/main/pocket_hero.svg
-  tags:
-    - llm
-    - gguf
-    - gpu
-    - cpu
-    - qwen
-    - qwen3.5
-    - moe
-  last_checked: "2026-07-29"
-  overrides:
-    backend: llama-cpp
-    known_usecases:
-      - chat
-    options:
-      - use_jinja:true
-    parameters:
-      model: POCKET-35B-Q4_K_M.gguf
-    template:
-      use_tokenizer_template: true
-  files:
-    - filename: POCKET-35B-Q4_K_M.gguf
-      uri: huggingface://FINAL-Bench/POCKET-35B-GGUF/POCKET-35B-Q4_K_M.gguf
-      sha256: 6f479f637c8fb932df39b9cfabdc454568eee48c0e7c0584e1815a27558e8ffe
-  variants:
-    - model: pocket-35b-q3-k-m
-    - model: pocket-35b-q2-k
-    - model: pocket-35b-iq1-m
-- !!merge <<: *pocket-35b
-  name: pocket-35b-q3-k-m
-  overrides:
-    backend: llama-cpp
-    known_usecases:
-      - chat
-    options:
-      - use_jinja:true
-    parameters:
-      model: POCKET-35B-Q3_K_M.gguf
-    template:
-      use_tokenizer_template: true
-  files:
-    - filename: POCKET-35B-Q3_K_M.gguf
-      uri: huggingface://FINAL-Bench/POCKET-35B-GGUF/POCKET-35B-Q3_K_M.gguf
-      sha256: 9ab4184f0f5af0cc1cf8eee7e553664b692c3f837a8868c4a16137bb3a3c97a2
-  variants: []
-- !!merge <<: *pocket-35b
-  name: pocket-35b-q2-k
-  overrides:
-    backend: llama-cpp
-    known_usecases:
-      - chat
-    options:
-      - use_jinja:true
-    parameters:
-      model: POCKET-35B-Q2_K.gguf
-    template:
-      use_tokenizer_template: true
-  files:
-    - filename: POCKET-35B-Q2_K.gguf
-      uri: huggingface://FINAL-Bench/POCKET-35B-GGUF/POCKET-35B-Q2_K.gguf
-      sha256: 2567ed710fb5b5bdf0df99ecfa241ab1a2b35edc618d2830b91d468e3a3ce191
-  variants: []
-- !!merge <<: *pocket-35b
-  name: pocket-35b-iq1-m
-  overrides:
-    backend: llama-cpp
-    known_usecases:
-      - chat
-    options:
-      - use_jinja:true
-    parameters:
-      model: POCKET-35B-IQ1_M.gguf
-    template:
-      use_tokenizer_template: true
-  files:
-    - filename: POCKET-35B-IQ1_M.gguf
-      uri: huggingface://FINAL-Bench/POCKET-35B-GGUF/POCKET-35B-IQ1_M.gguf
-      sha256: c56c77d158786f6dfb084e8cf3467456668e400cc7632c366cc0444b9f8565a1
-  variants: []
 - name: qwen3.5-35b-a3b-apex
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls: