chore(gallery): add Gemma 4 E4B Heretic variants

Add Q4_K_M and Q8_0 builds with the BF16 vision projector for llama.cpp.
Pin all three assets to a Hugging Face revision and document installation.

Assisted-by: Codex:gpt-6

docs/content/features/model-gallery.md

@@ -39,6 +39,25 @@ Both views use the same model selection and store the view, search, filter, and
 selection in the URL. Installing from Explore does not move you away from the
 catalog; the entry updates in place when the operation finishes.
 
+## Gemma 4 E4B Heretic
+
+[Gemma 4 E4B Heretic](https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic)
+is an abliterated version of Gemma 4 E4B IT. The gallery includes Q4_K_M and Q8_0
+GGUF builds for llama.cpp. Both include the BF16 vision projector for image input
+and use the embedded chat template with a 32,768-token context by default.
+
+Install with automatic variant selection:
+
+```bash
+local-ai models install gemma-4-e4b-heretic-q4
+```
+
+To select the Q8_0 build explicitly:
+
+```bash
+local-ai models install --variant gemma-4-e4b-heretic-q8 gemma-4-e4b-heretic-q4
+```
+
 ## Cyber-Ornith 1.5 9B
 
 Cyber-Ornith 1.5 is a Qwen3.5 fine-tune for security auditing, terminal tasks, and tool use.

gallery/index.yaml

@@ -13951,6 +13951,100 @@
     - filename: llama-cpp/mmproj/gemma-4-E4B-it-qat-q4_0-gguf/gemma-4-E4B-it-mmproj.gguf
       uri: https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-gguf/resolve/main/gemma-4-E4B-it-mmproj.gguf
       sha256: 7498a37cb619e55f2fcf87eb931f56e99389ed6d432e4c5c66110694c0d65578
+- name: gemma-4-e4b-heretic-q4
+  variants:
+    - model: gemma-4-e4b-heretic-q8
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic
+    - https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF
+  license: apache-2.0
+  icon: https://ai.google.dev/gemma/images/gemma4_banner.png
+  description: |
+    Gemma 4 E4B Heretic is llmfan46's abliterated version of Gemma 4 E4B IT.
+    This entry uses the Q4_K_M GGUF and BF16 vision projector for chat
+    and image input, with a 32,768-token context by default.
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - gemma4
+    - multimodal
+    - reasoning
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/gemma-4-e4b-heretic/gemma-4-E4B-it-mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/gemma-4-e4b-heretic/gemma-4-E4B-it-ultra-uncensored-heretic-Q4_K_M.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: 64
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/gemma-4-e4b-heretic/gemma-4-E4B-it-ultra-uncensored-heretic-Q4_K_M.gguf
+      uri: https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF/resolve/1465f37b7dbd15e91241ae78ffebecb9f25e15de/gemma-4-E4B-it-ultra-uncensored-heretic-Q4_K_M.gguf
+      sha256: f9dbbe3bdf396f65aec4e801516a1b868a510d96225417a8aa06763e3c5b97dc
+    - filename: llama-cpp/mmproj/gemma-4-e4b-heretic/gemma-4-E4B-it-mmproj-BF16.gguf
+      uri: https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF/resolve/1465f37b7dbd15e91241ae78ffebecb9f25e15de/gemma-4-E4B-it-mmproj-BF16.gguf
+      sha256: ffa64aebf7144bbadd5a1e143b77794d88e76a81cc0168d91de0770eb49e88e0
+- name: gemma-4-e4b-heretic-q8
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic
+    - https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF
+  license: apache-2.0
+  icon: https://ai.google.dev/gemma/images/gemma4_banner.png
+  description: |
+    Gemma 4 E4B Heretic is llmfan46's abliterated version of Gemma 4 E4B IT.
+    This entry uses the Q8_0 GGUF and BF16 vision projector for chat
+    and image input, with a 32,768-token context by default.
+  tags:
+    - llm
+    - gguf
+    - cpu
+    - gpu
+    - gemma4
+    - multimodal
+    - reasoning
+  overrides:
+    backend: llama-cpp
+    context_size: 32768
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+      - vision
+    mmproj: llama-cpp/mmproj/gemma-4-e4b-heretic/gemma-4-E4B-it-mmproj-BF16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      model: llama-cpp/models/gemma-4-e4b-heretic/gemma-4-E4B-it-ultra-uncensored-heretic-Q8_0.gguf
+      temperature: 1
+      top_p: 0.95
+      top_k: 64
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/gemma-4-e4b-heretic/gemma-4-E4B-it-ultra-uncensored-heretic-Q8_0.gguf
+      uri: https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF/resolve/1465f37b7dbd15e91241ae78ffebecb9f25e15de/gemma-4-E4B-it-ultra-uncensored-heretic-Q8_0.gguf
+      sha256: c1543610bcceeba8f51bd7cf38f373d2a002265f8873149aecae8a200b8fe4ba
+    - filename: llama-cpp/mmproj/gemma-4-e4b-heretic/gemma-4-E4B-it-mmproj-BF16.gguf
+      uri: https://huggingface.co/llmfan46/gemma-4-E4B-it-ultra-uncensored-heretic-GGUF/resolve/1465f37b7dbd15e91241ae78ffebecb9f25e15de/gemma-4-E4B-it-mmproj-BF16.gguf
+      sha256: ffa64aebf7144bbadd5a1e143b77794d88e76a81cc0168d91de0770eb49e88e0
 - name: gemma-4-e4b-hauhaucs-aggressive-q4
   variants:
     - model: gemma-4-e4b-hauhaucs-aggressive-q5