From 9bc69c9e5f67942db5e7ec818f500f355ba56465 Mon Sep 17 00:00:00 2001
From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com>
Date: Sat, 6 Jun 2026 13:52:46 +0200
Subject: [PATCH] chore(model gallery): :robot: add 1 new models via gallery
 agent (#10200)

chore(model gallery): :robot: add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
---
 gallery/index.yaml | 53 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 37ff7cd15..f6089b9b4 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,57 @@
 ---
+- name: "gemma-4-12b-it-qat-q4_0"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/google/gemma-4-12B-it-qat-q4_0-gguf
+  description: |
+    Hugging Face |
+    GitHub |
+    Launch Blog |
+    Documentation
+
+    License: Apache 2.0 | Authors: Google DeepMind
+
+    > [!Note]
+    > This model card is for the new versions of the Gemma 4 family optimized with Quantization-Aware Training (QAT), which allows preserving similar quality to bfloat16 while dramatically reducing the memory requirements to load the model.
+    > Four versions of the QAT checkpoints are available:
+    > * **Unquantized QAT checkpoints** (Q4_0): Half-precision weights extracted from the QAT pipeline, ideal for custom downstream compilation and research. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B, and their drafter models.
+    > * **GGUF** (Q4_0): Ready-to-deploy formats for broad ecosystem compatibility. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B.
+    > * **Mobile-optimized** (wNa8o8): A custom schema engineered explicitly for mobile hardware efficiency. It features targeted 2-bit decoding layers, optimized KV caches, and static activations to maximize VRAM savings. Available for Gemma 4 E2B and E4B.
+    > * **Compressed Tensors** (w4a16): QAT checkpoints serialized in the compressed-tensors format for native, optimized inference with vLLM. Available for Gemma 4 E2B, E4B, 12B
+
+    ...
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+  icon: https://ai.google.dev/gemma/images/gemma4_banner.png
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    mmproj: llama-cpp/mmproj/gemma-4-12B-it-qat-q4_0-gguf/mmproj-gemma-4-12b-it-qat-q4_0.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/gemma-4-12B-it-qat-q4_0-gguf/gemma-4-12b-it-qat-q4_0.gguf
+      repeat_penalty: 1
+      temperature: 1
+      top_k: 64
+      top_p: 0.95
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/gemma-4-12B-it-qat-q4_0-gguf/gemma-4-12b-it-qat-q4_0.gguf
+      sha256: faff1a63667fac17ac5e777f47114688fcefea96e220e211aaa8d62c2c4561f1
+      uri: https://huggingface.co/google/gemma-4-12B-it-qat-q4_0-gguf/resolve/main/gemma-4-12b-it-qat-q4_0.gguf
+    - filename: llama-cpp/mmproj/gemma-4-12B-it-qat-q4_0-gguf/mmproj-gemma-4-12b-it-qat-q4_0.gguf
+      sha256: e70b0e5cd80323d5d588b4ed06780356b7b1ba03995a4b8164c6ae9db0ff5989
+      uri: https://huggingface.co/google/gemma-4-12B-it-qat-q4_0-gguf/resolve/main/mmproj-gemma-4-12b-it-qat-q4_0.gguf
 - name: "step-3.7-flash"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls: