devquasar/qwen.qwen3-coder-480b-a35b-instruct-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": [
      "Qwen/Qwen3-Coder-480B-A35B-Instruct"
    ],
    "pipeline_tag": "text-generation",
    "frontmatter": {
      "base_model": [
        "Qwen/Qwen3-Coder-480B-A35B-Instruct"
      ],
      "pipeline_tag": "text-generation"
    },
    "hero_image_url": "https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png",
    "summary": "Q2 performace result on dual RTX5090 with 20 layers offloaded to GPU: | model                          |       size |     params | backend    | ngl |            test |                  t/s | | ------------------------------ | ---------: | ---------: | ---------- | --: | --------------: | -------------------: | | qwen3moe ?B Q2_K - Medium      | 162.66 GiB |   480.15 B | CUDA       |  20 |           pp512 |         90.09 ± 1.14 | | qwen3moe ?B Q2_K - Medium      | 162.66 GiB |   480.15 B | CUDA       |  20 |           tg128 |         12.51 ± 0.11 |  'Make knowledge free for everyone' Quantized version of: Qwen/Qwen3-Coder-480B-A35B-Instruct",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model:\n- Qwen/Qwen3-Coder-480B-A35B-Instruct\npipeline_tag: text-generation\n---\n\nQ2 performace result on dual RTX5090 with 20 layers offloaded to GPU:\n| model                          |       size |     params | backend    | ngl |            test |                  t/s |\n| ------------------------------ | ---------: | ---------: | ---------- | --: | --------------: | -------------------: |\n| qwen3moe ?B Q2_K - Medium      | 162.66 GiB |   480.15 B | CUDA       |  20 |           pp512 |         90.09 ± 1.14 |\n| qwen3moe ?B Q2_K - Medium      | 162.66 GiB |   480.15 B | CUDA       |  20 |           tg128 |         12.51 ± 0.11 |\n\n\n\n[<img src=\"https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png\" width=\"200\"/>](https://devquasar.com)\n\n'Make knowledge free for everyone'\n\nQuantized version of: [Qwen/Qwen3-Coder-480B-A35B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct)\n<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "text-generation",
    "base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct",
    "base_model:quantized:Qwen/Qwen3-Coder-480B-A35B-Instruct",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 383,
  "gated": false,
  "private": false,
  "last_modified": "2025-07-24T10:32:00.000Z",
  "created_at": "2025-07-23T00:51:53.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "68803229b642a69481a8cb51",
  "id": "DevQuasar/Qwen.Qwen3-Coder-480B-A35B-Instruct-GGUF",
  "modelId": "DevQuasar/Qwen.Qwen3-Coder-480B-A35B-Instruct-GGUF",
  "sha": "1eb2546bc88dec2850305ae9ab72f8a418a38a4d",
  "createdAt": "2025-07-23T00:51:53.000Z",
  "lastModified": "2025-07-24T10:32:00.000Z",
  "author": "DevQuasar",
  "downloads": 383,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 245
}