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

gallery/index.yaml

@@ -3127,7 +3127,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -3145,7 +3145,7 @@
   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:
@@ -3163,7 +3163,7 @@
   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:
@@ -6781,7 +6781,7 @@
       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
@@ -22489,3 +22489,44 @@
     - filename: PokeeAI.pokee_research_7b.Q4_K_M.gguf
       sha256: 4cf6e52b51f3595631b6e17ad2d5a5c8499d2e646cf9452dd32fb5ff7bbb37dd
       uri: huggingface://DevQuasar/PokeeAI.pokee_research_7b-GGUF/PokeeAI.pokee_research_7b.Q4_K_M.gguf
+- !!merge <<: *llama3
+  name: "ling-mini-base-2.0-15t-i1"
+  urls:
+    - https://huggingface.co/mradermacher/Ling-mini-base-2.0-15T-i1-GGUF
+  description: |
+    **Model Name:** Ling-mini-base-2.0-15T
+    **Base Model:** [inclusionAI/Ling-mini-base-2.0-15T](https://huggingface.co/inclusionAI/Ling-mini-base-2.0-15T)
+    **Model Type:** Mixture of Experts (MoE) Language Model
+    **Size:** 16B total parameters (1.4B activated per token)
+    **Context Length:** Up to 128K tokens (with YaRN)
+    **Training Data:** 15 trillion high-quality tokens
+    **License:** MIT
+
+    ---
+
+    ### 🔍 Overview
+    Ling-mini-base-2.0-15T is a compact yet powerful **MoE-based LLM** that achieves **top-tier performance** comparable to much larger dense models. With only **1.4B activated parameters per token**, it delivers **7× equivalent dense performance**, making it highly efficient for both inference and training.
+
+    ### ⚡ Key Features
+    - **High Efficiency:** 1/32 expert activation ratio enables fast inference (300+ tokens/sec on H20).
+    - **Long Context:** Supports up to **128K tokens** via YaRN, ideal for long-form reasoning and document analysis.
+    - **FP8 Training:** Open-sourced FP8 mixed-precision training solution for efficient fine-tuning.
+    - **Strong Reasoning:** Excels in coding, math, and knowledge-intensive tasks (AIME, HMMT, MMLU-Pro).
+
+    ### 📦 Use Cases
+    - Low-resource inference with high performance
+    - Long-context applications (legal, technical, research documents)
+    - Research and fine-tuning on MoE architectures
+
+    ### 📌 Model Availability
+    - **Original Base Model (FP16/BF16):** [inclusionAI/Ling-mini-base-2.0-15T](https://huggingface.co/inclusionAI/Ling-mini-base-2.0-15T)
+    - **Quantized GGUF Versions:** [mradermacher/Ling-mini-base-2.0-15T-i1-GGUF](https://huggingface.co/mradermacher/Ling-mini-base-2.0-15T-i1-GGUF) (for local inference)
+
+    > ✅ *For the original, unquantized model description and best performance — use the base model on Hugging Face.*
+  overrides:
+    parameters:
+      model: Ling-mini-base-2.0-15T.i1-Q4_K_M.gguf
+  files:
+    - filename: Ling-mini-base-2.0-15T.i1-Q4_K_M.gguf
+      sha256: 100292bc1cb37d5e59e0e97e2c53926e263567241a95fa8a0f06f165e89147a5
+      uri: huggingface://mradermacher/Ling-mini-base-2.0-15T-i1-GGUF/Ling-mini-base-2.0-15T.i1-Q4_K_M.gguf