teichai/qwen3-4b-instruct-2507-gemini-3-pro-preview-distill-gguf overview

{
  "metadata": {},
  "card_data": {
    "tags": [
      "gguf",
      "llama.cpp",
      "unsloth",
      "unsloth",
      "qwen3"
    ],
    "datasets": [
      "TeichAI/gemini-3-pro-preview-high-reasoning-1000x"
    ],
    "base_model": [
      "TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill"
    ],
    "frontmatter": {
      "tags": [
        "gguf",
        "llama.cpp",
        "unsloth",
        "unsloth",
        "qwen3"
      ],
      "datasets": [
        "TeichAI/gemini-3-pro-preview-high-reasoning-1000x"
      ],
      "base_model": [
        "TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill"
      ]
    },
    "hero_image_url": "",
    "summary": "This model was trained on a **Gemini 3 Pro Preview** dataset with a high reasoning effort. The reasoning summaries were then formatted out of the dataset and the model was finetuned on the final answers only. --- This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\ntags:\n- gguf\n- llama.cpp\n- unsloth\n- unsloth\n- qwen3\ndatasets:\n- TeichAI/gemini-3-pro-preview-high-reasoning-1000x\nbase_model:\n- TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill\n---\n\n# Qwen3 4B Instruct 2507 - Gemini 3 Pro Preview (No Reasoning) Distill\n\nThis model was trained on a **Gemini 3 Pro Preview** dataset with a high reasoning effort.\n\nThe reasoning summaries were then formatted out of the dataset and the model was finetuned on the final answers only.\n\n- 🧬 Datasets:\n  - `TeichAI/gemini-3-pro-preview-high-reasoning-1000x`\n\n- 🏗 Base Model:\n  - `unsloth/Qwen3-4B-Instruct-2507`\n \n- ⚡ Use cases:\n  - Coding\n  - Science\n\n- ∑ Stats (Dataset)\n  - Costs: $ 32.7 (USD)\n  - Total tokens (input + output): 2.73 M\n\n---\n\nThis qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.\n\n## Ollama\nAn Ollama Modelfile is included for easy deployment.\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "qwen3",
    "llama.cpp",
    "unsloth",
    "dataset:TeichAI/gemini-3-pro-preview-high-reasoning-1000x",
    "base_model:TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill",
    "base_model:quantized:TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 8,
  "downloads": 1029,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-24T09:27:15.000Z",
  "created_at": "2025-12-24T07:47:28.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "694b9a901c2c18ff21a36a0a",
  "id": "TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill-GGUF",
  "modelId": "TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill-GGUF",
  "sha": "bc99a1b6a2dfc16121cf5040637cf882d74801c3",
  "createdAt": "2025-12-24T07:47:28.000Z",
  "lastModified": "2025-12-24T09:27:15.000Z",
  "author": "TeichAI",
  "downloads": 1029,
  "likes": 8,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 19
}