aaryank/youtu-llm-2b-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "tencent/Youtu-LLM-2B",
    "base_model_relation": "quantized",
    "language": [
      "en",
      "zh"
    ],
    "library_name": "gguf",
    "license": "other",
    "license_name": "youtu-llm",
    "license_link": "https://huggingface.co/tencent/Youtu-LLM-2B/blob/main/LICENSE.txt",
    "pipeline_tag": "text-generation",
    "tags": [
      "text-generation-inference",
      "agent",
      "code",
      "128k",
      "mla",
      "gguf"
    ],
    "frontmatter": {
      "base_model": "tencent/Youtu-LLM-2B",
      "base_model_relation": "quantized",
      "language": [
        "en",
        "zh"
      ],
      "library_name": "gguf",
      "license": "other",
      "license_name": "youtu-llm",
      "license_link": "https://huggingface.co/tencent/Youtu-LLM-2B/blob/main/LICENSE.txt",
      "pipeline_tag": "text-generation",
      "tags": [
        "text-generation-inference",
        "agent",
        "code",
        "128k",
        "mla",
        "gguf"
      ]
    },
    "hero_image_url": "https://huggingface.co/tencent/Youtu-LLM-2B/resolve/main/assets/youtu-llm-logo.png",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: tencent/Youtu-LLM-2B\nbase_model_relation: quantized\nlanguage:\n  - en\n  - zh\nlibrary_name: gguf\nlicense: other\nlicense_name: youtu-llm\nlicense_link: https://huggingface.co/tencent/Youtu-LLM-2B/blob/main/LICENSE.txt\npipeline_tag: text-generation\ntags:\n  - text-generation-inference\n  - agent\n  - code\n  - 128k\n  - mla\n  - gguf\n---\n\n# Youtu-LLM-2B-GGUF\n\n<div align=\"center\">\n<img src=\"https://huggingface.co/tencent/Youtu-LLM-2B/resolve/main/assets/youtu-llm-logo.png\" alt=\"Youtu-LLM Logo\" height=\"100px\">\n</div>\n\n## Description\n\nThis repository contains **GGUF** format model files for [Tencent's Youtu-LLM-2B](https://huggingface.co/tencent/Youtu-LLM-2B).\n\n**Youtu-LLM-2B** is a highly efficient 1.96B parameter model featuring a Dense MLA architecture and a native **128K context window**. Despite its small size, it supports **Agentic capabilities** and \"Reasoning Mode\" (Chain of Thought), outperforming many larger models in STEM, coding, and agentic benchmarks.\n\n## Evaluation Results\n\n<img src=\"https://huggingface.co/tencent/Youtu-LLM-2B/resolve/main/assets/general_agentic_instruct.png\" alt=\"Comparison between Youtu-LLM-2B and baselines\">\n\n## Files & Quantization\n\nTo see the available files, please verify the **Files and versions** tab.\n\n## How to Run (llama.cpp)\n\n**Note:** This model uses the **Dense MLA** architecture. Please ensure you are using the latest version of `llama.cpp` to support this architecture correctly.\n\n**Recommended Parameters:**\nThis model supports two modes. Adjust your temperature accordingly:\n*   **Reasoning Mode (CoT):** Temperature `1.0` (Recommended for complex logic/math).\n*   **Normal Mode:** Temperature `0.7` (Recommended for chat/stability).\n*   **Context:** `-c` (Supports up to 131072).\n\n### CLI Example\n\n```bash\n./llama-cli -m Youtu-LLM-2B.Q4_K_M.gguf \\\n  -c 8192 \\\n  --temp 1.0 \\\n  --top-p 0.95 \\\n  -p \"User: Explain the theory of relativity.\\nAssistant:\" \\\n  -cnv\n```\n\n### Server Example\n\n```bash\n./llama-server -m Youtu-LLM-2B.Q4_K_M.gguf \\\n  --port 8080 \\\n  --host 0.0.0.0 \\\n  -c 16384 \\\n  -ngl 99\n```",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-generation-inference",
    "agent",
    "code",
    "128k",
    "mla",
    "text-generation",
    "en",
    "zh",
    "base_model:tencent/Youtu-LLM-2B",
    "base_model:quantized:tencent/Youtu-LLM-2B",
    "license:other",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 11,
  "downloads": 229,
  "gated": false,
  "private": false,
  "last_modified": "2026-01-01T22:00:44.000Z",
  "created_at": "2026-01-01T21:20:00.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "gguf"
}

{
  "_id": "6956e5005f70da4f068ef3aa",
  "id": "AaryanK/Youtu-LLM-2B-GGUF",
  "modelId": "AaryanK/Youtu-LLM-2B-GGUF",
  "sha": "af5ea6525fbc79c0650516225f817f850380dbef",
  "createdAt": "2026-01-01T21:20:00.000Z",
  "lastModified": "2026-01-01T22:00:44.000Z",
  "author": "AaryanK",
  "downloads": 229,
  "likes": 11,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "gguf",
  "siblings_count": 17
}