flexan/dqn-labs-community-dqnmath-v0.2-2b-gguf overview

{
  "metadata": {},
  "card_data": {
    "library_name": "mlx",
    "license": "apache-2.0",
    "license_link": "https://huggingface.co/Qwen/Qwen3.5-2B/blob/main/LICENSE",
    "pipeline_tag": "text-generation",
    "base_model": "DQN-Labs-Community/dqnMath-v0.2-2B",
    "tags": [
      "mlx"
    ],
    "frontmatter": {
      "library_name": "mlx",
      "license": "apache-2.0",
      "license_link": "https://huggingface.co/Qwen/Qwen3.5-2B/blob/main/LICENSE",
      "pipeline_tag": "text-generation",
      "base_model": "DQN-Labs-Community/dqnMath-v0.2-2B",
      "tags": [
        "mlx"
      ]
    },
    "hero_image_url": "",
    "summary": "These are the GGUF files for DQN-Labs-Community/dqnMath-v0.2-2B.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlibrary_name: mlx\nlicense: apache-2.0\nlicense_link: https://huggingface.co/Qwen/Qwen3.5-2B/blob/main/LICENSE\npipeline_tag: text-generation\nbase_model: DQN-Labs-Community/dqnMath-v0.2-2B\ntags:\n- mlx\n---\n\n# GGUF Files for dqnMath-v0.2-2B\r\n\r\nThese are the GGUF files for [DQN-Labs-Community/dqnMath-v0.2-2B](https://huggingface.co/DQN-Labs-Community/dqnMath-v0.2-2B).\r\n\r\n## Downloads\r\n\r\n| GGUF Link | Quantization | Description |\r\n| ---- | ----- | ----------- |\r\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q2_K.gguf) | Q2_K | Lowest quality |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q3_K_S.gguf) | Q3_K_S |  |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.IQ3_S.gguf) | IQ3_S | Integer quant, preferable over Q3_K_S |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.IQ3_M.gguf) | IQ3_M | Integer quant |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q3_K_M.gguf) | Q3_K_M |  |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q3_K_L.gguf) | Q3_K_L |  |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.IQ4_XS.gguf) | IQ4_XS | Integer quant |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q4_K_S.gguf) | Q4_K_S | Fast with good performance |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q4_K_M.gguf) | Q4_K_M | **Recommended:** Perfect mix of speed and performance |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q5_K_S.gguf) | Q5_K_S |  |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q5_K_M.gguf) | Q5_K_M |  |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q6_K.gguf) | Q6_K | Very good quality |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.Q8_0.gguf) | Q8_0 | Best quality |\n| [Download](https://huggingface.co/Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF/resolve/main/dqnMath-v0.2-2B.f16.gguf) | f16 | Full precision, don't bother; use a quant |\r\n\r\n## Note from Flexan\r\n\r\nI provide GGUFs and quantizations of publicly available models that do not have a GGUF equivalent available yet,\r\nusually for models **I deem interesting and wish to try out**.\r\n\r\nIf there are some quants missing that you'd like me to add, you may request one in the community tab.\r\nIf you want to request a public model to be converted, you can also request that in the community tab.\r\nIf you have questions regarding this model, please refer to [the original model repo](https://huggingface.co/DQN-Labs-Community/dqnMath-v0.2-2B).\r\n\r\nYou can find more info about me and what I do [here](https://huggingface.co/Flexan/Flexan).\n\n# DQN-Labs-Community/dqnMath-v0.2-2B\n\nThis model [DQN-Labs-Community/dqnMath-v0.2-2B](https://huggingface.co/DQN-Labs-Community/dqnMath-v0.2-2B) was\nconverted to MLX format from [Qwen/Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B)\nusing mlx-lm version **0.30.7**.\n\n## Use with mlx\n\n```bash\npip install mlx-lm\n```\n\n```python\nfrom mlx_lm import load, generate\n\nmodel, tokenizer = load(\"DQN-Labs-Community/dqnMath-v0.2-2B\")\n\nprompt = \"hello\"\n\nif tokenizer.chat_template is not None:\n    messages = [{\"role\": \"user\", \"content\": prompt}]\n    prompt = tokenizer.apply_chat_template(\n        messages, add_generation_prompt=True, return_dict=False,\n    )\n\nresponse = generate(model, tokenizer, prompt=prompt, verbose=True)\n```",
    "related_quantizations": []
  },
  "tags": [
    "mlx",
    "gguf",
    "text-generation",
    "base_model:DQN-Labs-Community/dqnMath-v0.2-2B",
    "base_model:quantized:DQN-Labs-Community/dqnMath-v0.2-2B",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 108,
  "gated": false,
  "private": false,
  "last_modified": "2026-03-13T08:45:57.000Z",
  "created_at": "2026-03-13T08:43:48.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "mlx"
}

{
  "_id": "69b3ce447129ed796f6643bd",
  "id": "Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF",
  "modelId": "Flexan/DQN-Labs-Community-dqnMath-v0.2-2B-GGUF",
  "sha": "ad05e1bb84cc817d03b7e412a7b660e0a0b3a0e2",
  "createdAt": "2026-03-13T08:43:48.000Z",
  "lastModified": "2026-03-13T08:45:57.000Z",
  "author": "Flexan",
  "downloads": 108,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "mlx",
  "siblings_count": 16
}