brittlewis12/deepseek-r1-0528-qwen3-8b-gguf overview

{
  "metadata": {},
  "card_data": {
    "base_model": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
    "pipeline_tag": "text-generation",
    "inference": true,
    "language": [
      "en"
    ],
    "license": "mit",
    "model_creator": "deepseek-ai",
    "model_name": "DeepSeek-R1-0528-Qwen3-8B",
    "model_type": "qwen3",
    "quantized_by": "brittlewis12",
    "tags": [
      "reasoning",
      "deepseek",
      "qwen3"
    ],
    "frontmatter": {
      "base_model": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
      "pipeline_tag": "text-generation",
      "inference": "true",
      "language": [
        "en"
      ],
      "license": "mit",
      "model_creator": "deepseek-ai",
      "model_name": "DeepSeek-R1-0528-Qwen3-8B",
      "model_type": "qwen3",
      "quantized_by": "brittlewis12",
      "tags": [
        "reasoning",
        "deepseek",
        "qwen3"
      ]
    },
    "hero_image_url": "https://pbs.twimg.com/profile_images/1744049151241797632/0mIP-P9e_400x400.jpg",
    "summary": "**Original model**: DeepSeek-R1-0528-Qwen3-8B **Model creator**: DeepSeek AI > We distilled the chain-of-thought from DeepSeek-R1-0528 to post-train Qwen3 8B Base, obtaining DeepSeek-R1-0528-Qwen3-8B. This model achieves state-of-the-art (SOTA) performance among open-source models on the AIME 2024, surpassing Qwen3 8B by +10.0% and matching the performance of Qwen3-235B-thinking. We believe that the chain-of-thought from DeepSeek-R1-0528 will hold significant importance for both academic research on reasoning models and industrial development focused on small-scale models. This repo contains GGUF format model files for DeepSeek AI's _DeepSeek R1 0528 Qwen3 8B_. ### What is GGUF? GGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023. Converted with llama.cpp build b5536 (revision 2b13162), using autogguf-rs. ### Prompt template: DeepSeek R1 `` {{system_message}} {{prompt}} ` ### Notes from DeepSeek on Running Locally > Compared to previous versions of DeepSeek-R1, the usage recommendations for DeepSeek-R1-0528 have the following changes: > > - System prompt is supported now. > - It is not required to add \\n` at the beginning of the output to force the model into thinking pattern. > > The model architecture of DeepSeek-R1-0528-Qwen3-8B is identical to that of Qwen3-8B, but it shares the same tokenizer configuration as DeepSeek-R1-0528. ---",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B\npipeline_tag: text-generation\ninference: true\nlanguage:\n- en\nlicense: mit\nmodel_creator: deepseek-ai\nmodel_name: DeepSeek-R1-0528-Qwen3-8B\nmodel_type: qwen3\nquantized_by: brittlewis12\ntags:\n- reasoning\n- deepseek\n- qwen3\n---\n\n# DeepSeek R1 0528 Qwen3 8B GGUF\n\n**Original model**: [DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B)\n\n**Model creator**: [DeepSeek AI](https://huggingface.co/deepseek-ai)\n\n> We distilled the chain-of-thought from DeepSeek-R1-0528 to post-train Qwen3 8B Base, obtaining DeepSeek-R1-0528-Qwen3-8B. This model achieves state-of-the-art (SOTA) performance among open-source models on the AIME 2024, surpassing Qwen3 8B by +10.0% and matching the performance of Qwen3-235B-thinking. We believe that the chain-of-thought from DeepSeek-R1-0528 will hold significant importance for both academic research on reasoning models and industrial development focused on small-scale models.\n\nThis repo contains GGUF format model files for DeepSeek AI's _DeepSeek R1 0528 Qwen3 8B_.\n\n### What is GGUF?\n\nGGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023.\n\nConverted with llama.cpp build b5536 (revision [2b13162](https://github.com/ggml-org/llama.cpp/commits/2b131621e60d8ec2cc961201beb6773ab37b6b69)), using [autogguf-rs](https://github.com/brittlewis12/autogguf-rs).\n\n### Prompt template: [DeepSeek R1](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B/blob/main/tokenizer_config.json#L34)\n\n```\n{{system_message}}\n\n<｜User｜>{{prompt}}<｜Assistant｜>\n\n```\n\n### Notes from DeepSeek on Running Locally\n\n> Compared to previous versions of DeepSeek-R1, the usage recommendations for DeepSeek-R1-0528 have the following changes:\n> \n> - System prompt is supported now.\n> - It is not required to add `<think>\\n` at the beginning of the output to force the model into thinking pattern.\n> \n> The model architecture of DeepSeek-R1-0528-Qwen3-8B is identical to that of Qwen3-8B, but it shares the same tokenizer configuration as DeepSeek-R1-0528.\n\n\n---\n\n## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac!\n\n![cnvrs.ai](https://pbs.twimg.com/profile_images/1744049151241797632/0mIP-P9e_400x400.jpg)\n\n[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device:\n- create & save **Characters** with custom system prompts & temperature settings\n- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)!\n    * or, use an API key with the chat completions-compatible model provider of your choice -- ChatGPT, Claude, Gemini, DeepSeek, & more!\n- make it your own with custom **Theme colors**\n- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggml-org/llama.cpp), with **haptics** during response streaming!\n- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)!\n    * if you **already have the app**, download DeepSeek R1 0528 Qwen3 8B now! \n    * <cnvrsai:///models/search/hf?id=brittlewis12/DeepSeek-R1-0528-Qwen3-8B-GGUF>\n- follow [cnvrs on twitter](https://twitter.com/cnvrsai) to stay up to date\n\n---\n\n## Original Model Evaluation\n\n> We distilled the chain-of-thought from DeepSeek-R1-0528 to post-train Qwen3 8B Base, obtaining DeepSeek-R1-0528-Qwen3-8B. This model achieves state-of-the-art (SOTA) performance among open-source models on the AIME 2024, surpassing Qwen3 8B by +10.0% and matching the performance of Qwen3-235B-thinking.\n\n|                                | AIME 24 | AIME 25 | HMMT Feb 25 | GPQA Diamond | LiveCodeBench (2408-2505) |\n|--------------------------------|---------|---------|-------------|--------------|---------------------------|\n| Qwen3-235B-A22B\t                | 85.7    | 81.5    | 62.5        | 71.1         | 66.5                  |\n| Qwen3-32B                      | 81.4    | 72.9    | -           | 68.4         | -                         |\n| Qwen3-8B                      | 76.0   | 67.3    | -           | 62.0       | -                         |\n| Phi-4-Reasoning-Plus-14B       | 81.3    | 78.0    | 53.6        | 69.3         | -          |\n| Gemini-2.5-Flash-Thinking-0520 | 82.3    | 72.0    | 64.2        | 82.8         | 62.3                  |\n| o3-mini (medium)               | 79.6    | 76.7    | 53.3        | 76.8         | 65.9                     |\n| **DeepSeek-R1-0528-Qwen3-8B**      | **86.0**   | **76.3**    | **61.5**        | **61.1**         | **60.5**                      |\n\n---\n\n## DeepSeek R1 0528 Qwen3 8B in cnvrs on iOS\n\n![deepseek-r1-qwen3-8b in cnvrs pt1](https://cdn-uploads.huggingface.co/production/uploads/63b64d7a889aa6707f155cdb/nsXnOaK6Sb-0PGvdY8ayy.png)\n![deepseek-r1-qwen3-8b in cnvrs pt2](https://cdn-uploads.huggingface.co/production/uploads/63b64d7a889aa6707f155cdb/4AnhMFL41EuIwhKuVaCGi.png)\n\n---",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "reasoning",
    "deepseek",
    "qwen3",
    "text-generation",
    "en",
    "base_model:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
    "base_model:quantized:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
    "license:mit",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 143,
  "gated": false,
  "private": false,
  "last_modified": "2025-05-30T00:31:10.000Z",
  "created_at": "2025-05-29T14:30:35.000Z",
  "pipeline_tag": "text-generation",
  "library_name": ""
}

{
  "_id": "68386f8bbfd22b0c2674a4eb",
  "id": "brittlewis12/DeepSeek-R1-0528-Qwen3-8B-GGUF",
  "modelId": "brittlewis12/DeepSeek-R1-0528-Qwen3-8B-GGUF",
  "sha": "871b8ae6b66842817b8f92b643bf0d9be356ba0b",
  "createdAt": "2025-05-29T14:30:35.000Z",
  "lastModified": "2025-05-30T00:31:10.000Z",
  "author": "brittlewis12",
  "downloads": 143,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "",
  "siblings_count": 31
}