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
@@ -22169,3 +22169,30 @@
     - filename: Zirel-2.i1-Q4_K_S.gguf
       sha256: 9856e987f5f59c874a8fe26ffb2a2c5b7c60b85186131048536b3f1d91a235a6
       uri: huggingface://mradermacher/Zirel-2-i1-GGUF/Zirel-2.i1-Q4_K_S.gguf
+- !!merge <<: *llama3
+  name: "ling-1t"
+  urls:
+    - https://huggingface.co/ubergarm2/Ling-1T-GGUF
+  description: |
+    **Ling-1T** is a 1-trillion-parameter, non-thinking flagship model from the Ling 2.0 series, designed for efficient, scalable reasoning at massive scale. Built with a **1/32 MoE (Mixture of Experts)** architecture, it activates ~50 billion parameters per token, enabling high-performance reasoning with optimized resource usage.
+
+    Trained on **20+ trillion high-quality, reasoning-dense tokens**, Ling-1T supports up to **128K context length** and leverages **Evo-CoT (Evolutionary Chain-of-Thought)** for progressive reasoning enhancement. It achieves **state-of-the-art performance** on complex benchmarks—including math, code generation, and logical reasoning—surpassing many closed-source models in accuracy and efficiency.
+
+    Key features:
+    - **FP8 mixed-precision training** for improved speed and memory efficiency
+    - **QK Normalization** and **aux-loss-free expert routing** for stable, scalable training
+    - **Syntax–Function–Aesthetics** reward system for high-quality front-end code and visual generation
+    - Strong performance on **AIME 25**, **BFCL V3**, and **ArtifactsBench**, ranking first among open-source models
+
+    Ideal for advanced reasoning, code synthesis, and multi-domain tasks, Ling-1T sets a new standard for open-source, efficient large language models.
+
+    > 📌 **Model Repository**: [huggingface.co/inclusionAI/Ling-1T](https://huggingface.co/inclusionAI/Ling-1T)
+    > 🚀 **Try Online**: [ZenMux](https://zenmux.ai/inclusionai/ling-1t)
+    > 🔗 **License**: MIT
+  overrides:
+    parameters:
+      model: IQ2_K
+  files:
+    - filename: IQ2_K
+      sha256: 77fda7661a2d3c8ab91f3d41c66ae15d8c621f08
+      uri: huggingface://ubergarm2/Ling-1T-GGUF/IQ2_K