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

gallery/index.yaml

@@ -3295,7 +3295,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -3313,7 +3313,7 @@
   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:
@@ -3331,7 +3331,7 @@
   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:
@@ -6949,7 +6949,7 @@
       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
@@ -23023,3 +23023,38 @@
     - filename: Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-PKDick-V.i1-Q4_K_M.gguf
       sha256: 6955283520e3618fe349bb75f135eae740f020d9d7f5ba38503482e5d97f6f59
       uri: huggingface://mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-PKDick-V-i1-GGUF/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-PKDick-V.i1-Q4_K_M.gguf
+- !!merge <<: *llama3
+  name: "nvidia.qwen3-nemotron-32b-rlbff"
+  urls:
+    - https://huggingface.co/DevQuasar/nvidia.Qwen3-Nemotron-32B-RLBFF-GGUF
+  description: |
+    **Model Name:** Qwen3-Nemotron-32B-RLBFF
+    **Base Model:** Qwen/Qwen3-32B
+    **License:** NVIDIA Open Model License
+    **Repository:** [nvidia/Qwen3-Nemotron-32B-RLBFF](https://huggingface.co/nvidia/Qwen3-Nemotron-32B-RLBFF)
+
+    **Description:**
+    Qwen3-Nemotron-32B-RLBFF is a 32-billion-parameter large language model fine-tuned from Qwen3-32B using the **RLBFF (Binary Flexible Feedback)** method. It is optimized to generate high-quality, helpful responses in standard reasoning mode, with significant improvements over the base model across key benchmarks.
+
+    The model was trained on the **HelpSteer3** dataset — a large-scale, human-annotated collection of instruction-response pairs with detailed feedback — to enhance response coherence, accuracy, and task alignment.
+
+    **Key Performance Metrics (as of Sept 2025):**
+    - **MT-Bench Score:** 9.50 (approaching GPT-4-Turbo)
+    - **Arena Hard V2:** 55.6% win rate
+    - **WildBench Score:** 70.33%
+
+    Despite its advanced performance, it achieves this at **less than 5% of the inference cost** of comparable models like DeepSeek R1, making it highly efficient for deployment on NVIDIA GPU platforms (Ampere/Hopper architectures).
+
+    **Use Case:** Ideal for applications requiring robust, cost-efficient, and high-quality text generation in complex reasoning and dialogue scenarios.
+
+    **Note:** This model is research-focused and intended for evaluation, experimentation, and development. Always review the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/) before use.
+
+    ✅ *Available via Hugging Face Transformers and vLLM for optimized inference.*
+    📎 *Citation: [Wang et al., 2025](https://arxiv.org/abs/2509.21319)*
+  overrides:
+    parameters:
+      model: nvidia.Qwen3-Nemotron-32B-RLBFF.Q4_K_M.gguf
+  files:
+    - filename: nvidia.Qwen3-Nemotron-32B-RLBFF.Q4_K_M.gguf
+      sha256: 5dfc9f1dc21885371b12a6e0857d86d6deb62b6601b4d439e4dfe01195a462f1
+      uri: huggingface://DevQuasar/nvidia.Qwen3-Nemotron-32B-RLBFF-GGUF/nvidia.Qwen3-Nemotron-32B-RLBFF.Q4_K_M.gguf