chore(model gallery): 🤖 add 1 new models via gallery agent

gallery/index.yaml

@@ -3309,7 +3309,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -3327,7 +3327,7 @@
   description: |
     google/gemma-3-12b-it is an open-source, state-of-the-art, lightweight, multimodal model built from the same research and technology used to create the Gemini models. It is capable of handling text and image input and generating text output. It has a large context window of 128K tokens and supports over 140 languages. The 12B variant has been fine-tuned using the instruction-tuning approach. Gemma 3 models are suitable for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes them deployable in environments with limited resources such as laptops, desktops, or your own cloud infrastructure.
   overrides:
     #mmproj: gemma-3-12b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-12b-it-Q4_K_M.gguf
   files:
@@ -3345,7 +3345,7 @@
   description: |
     Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. Gemma-3-4b-it is a 4 billion parameter model.
   overrides:
     #mmproj: gemma-3-4b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-4b-it-Q4_K_M.gguf
   files:
@@ -6963,7 +6963,7 @@
       sha256: 2756551de7d8ff7093c2c5eec1cd00f1868bc128433af53f5a8d434091d4eb5a
       uri: huggingface://Triangle104/Nano_Imp_1B-Q8_0-GGUF/nano_imp_1b-q8_0.gguf
 - &qwen25
   name: "qwen2.5-14b-instruct" ## Qwen2.5
   icon: https://avatars.githubusercontent.com/u/141221163
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
   license: apache-2.0
@@ -23363,3 +23363,27 @@
     - filename: Qwen3-Grand-Horror-Light-1.7B.Q4_K_M.gguf
       sha256: cbbb0c5f6874130a8ae253377fdc7ad25fa2c1e9bb45f1aaad88db853ef985dc
       uri: huggingface://mradermacher/Qwen3-Grand-Horror-Light-1.7B-GGUF/Qwen3-Grand-Horror-Light-1.7B.Q4_K_M.gguf
+- !!merge <<: *qwen3
+  name: "qwen3-nemotron-14b-brrm-i1"
+  urls:
+    - https://huggingface.co/mradermacher/Qwen3-Nemotron-14B-BRRM-i1-GGUF
+  description: |
+    **Qwen3-Nemotron-14B-BRRM** is a state-of-the-art **reward model** developed by NVIDIA, built upon the Qwen3-14B foundation. It implements a novel **two-turn reasoning framework**—*Adaptive Branching* and *Branch-Conditioned Rethinking*—to evaluate LLM-generated responses with greater precision.
+
+    Instead of making a single, broad judgment, it dynamically identifies the most critical evaluation dimensions (e.g., logical reasoning, computational accuracy) for each instance, then performs targeted deep analysis. This approach significantly reduces "judgment diffusion" and achieves **SOTA performance** across major benchmarks: **92.1% on RewardBench**, **85.9% on RM-Bench**, and **74.7% on RMB**.
+
+    Ideal for use in **RLHF pipelines**, this model excels at comparing responses and providing nuanced, human-aligned feedback. It's designed for advanced research and development in AI alignment and instruction tuning.
+
+    - **Base Model**: Qwen/Qwen3-14B
+    - **Type**: Reward Model (Two-Turn Reasoning)
+    - **Use Case**: Response evaluation, preference learning, alignment training
+    - **License**: NVIDIA Internal Scientific Research & Development License
+
+    > 🔗 *Available in GGUF format for local inference via tools like llama.cpp.*
+  overrides:
+    parameters:
+      model: Qwen3-Nemotron-14B-BRRM.i1-Q4_K_M.gguf
+  files:
+    - filename: Qwen3-Nemotron-14B-BRRM.i1-Q4_K_M.gguf
+      sha256: ab6af8750794b412adfd0b6aae6d8bcc5a242cbf0b1391e31c3542dbbbd9516a
+      uri: huggingface://mradermacher/Qwen3-Nemotron-14B-BRRM-i1-GGUF/Qwen3-Nemotron-14B-BRRM.i1-Q4_K_M.gguf