prithivmlmods/ministral-3-reasoning-2512-aio-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en",
      "fr",
      "es",
      "de",
      "it",
      "pt",
      "nl",
      "zh",
      "ja",
      "ko",
      "ar"
    ],
    "base_model": [
      "mistralai/Ministral-3-3B-Reasoning-2512",
      "mistralai/Ministral-3-8B-Reasoning-2512",
      "mistralai/Ministral-3-14B-Reasoning-2512"
    ],
    "library_name": "transformers",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "text-generation-inference",
      "llama.cpp",
      "f32"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en",
        "fr",
        "es",
        "de",
        "it",
        "pt",
        "nl",
        "zh",
        "ja",
        "ko",
        "ar"
      ],
      "base_model": [
        "mistralai/Ministral-3-3B-Reasoning-2512",
        "mistralai/Ministral-3-8B-Reasoning-2512",
        "mistralai/Ministral-3-14B-Reasoning-2512"
      ],
      "library_name": "transformers",
      "pipeline_tag": "image-text-to-text",
      "tags": [
        "text-generation-inference",
        "llama.cpp",
        "f32"
      ]
    },
    "hero_image_url": "https://www.nethype.de/huggingface_embed/quantpplgraph.png",
    "summary": "> The Ministral 3 Reasoning models (3B, 8B, and 14B variants from mistralai) are post-trained vision-language models specialized for advanced reasoning tasks like math, coding, and STEM applications, featuring a core language model (3.4B, 8.4B, or 13.5B parameters) paired with a 0.4B vision encoder for multimodal image analysis, supporting a 256k context window, multilingual capabilities, and edge deployment on hardware as low as 24GB VRAM/RAM when quantized (BF16 precision). Optimized with a recommended temperature of 0.7 and top_p=0.95 for reasoning, they use a distinctive chat template encouraging structured [THINK] inner monologue drafts in Markdown/LaTeX before final responses, enabling step-by-step problem-solving while maintaining strong performance in benchmarks like AIME25 (0.721 for 3B) and GPQA Diamond. Ideal for resource-efficient local inference via vLLM or Transformers, these Apache 2.0-licensed models excel in agentic workflows, function calling, and complex multimodal reasoning under constrained environments.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\n- fr\n- es\n- de\n- it\n- pt\n- nl\n- zh\n- ja\n- ko\n- ar\nbase_model:\n- mistralai/Ministral-3-3B-Reasoning-2512\n- mistralai/Ministral-3-8B-Reasoning-2512\n- mistralai/Ministral-3-14B-Reasoning-2512\nlibrary_name: transformers\npipeline_tag: image-text-to-text\ntags:\n- text-generation-inference\n- llama.cpp\n- f32\n---\n\n# **Ministral-3-Reasoning-2512-AIO-GGUF**\n\n> The [Ministral 3 Reasoning](https://huggingface.co/collections/mistralai/ministral-3) models (3B, 8B, and 14B variants from mistralai) are post-trained vision-language models specialized for advanced reasoning tasks like math, coding, and STEM applications, featuring a core language model (3.4B, 8.4B, or 13.5B parameters) paired with a 0.4B vision encoder for multimodal image analysis, supporting a 256k context window, multilingual capabilities, and edge deployment on hardware as low as 24GB VRAM/RAM when quantized (BF16 precision). Optimized with a recommended temperature of 0.7 and top_p=0.95 for reasoning, they use a distinctive chat template encouraging structured [THINK] inner monologue drafts in Markdown/LaTeX before final responses, enabling step-by-step problem-solving while maintaining strong performance in benchmarks like AIME25 (0.721 for 3B) and GPQA Diamond. Ideal for resource-efficient local inference via vLLM or Transformers, these Apache 2.0-licensed models excel in agentic workflows, function calling, and complex multimodal reasoning under constrained environments.\n\n## Ministral-3-14B-Reasoning-2512 [GGUF]\n\n| File Name | Quant Type | File Size | File Link |\n| - | - | - | - |\n| Ministral-3-14B-Reasoning-2512-BF16.gguf | BF16 | 27 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-BF16.gguf) |\n| Ministral-3-14B-Reasoning-2512-Q4_K_M.gguf | Q4_K_M | 8.24 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-Q4_K_M.gguf) |\n| Ministral-3-14B-Reasoning-2512-Q5_K_M.gguf | Q5_K_M | 9.62 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-Q5_K_M.gguf) |\n| Ministral-3-14B-Reasoning-2512-Q8_0.gguf | Q8_0 | 14.4 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-Q8_0.gguf) |\n| Ministral-3-14B-Reasoning-2512-BF16-mmproj.gguf | BF16-mmproj | 879 MB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-14B-Reasoning-2512-BF16-mmproj.gguf) |\n\n## Ministral-3-8B-Reasoning-2512 [GGUF]\n\n| File Name | Quant Type | File Size | File Link |\n| - | - | - | - |\n| Ministral-3-8B-Reasoning-2512-BF16.gguf | BF16 | 17 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-BF16.gguf) |\n| Ministral-3-8B-Reasoning-2512-Q4_K_M.gguf | Q4_K_M | 5.2 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-Q4_K_M.gguf) |\n| Ministral-3-8B-Reasoning-2512-Q5_K_M.gguf | Q5_K_M | 6.06 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-Q5_K_M.gguf) |\n| Ministral-3-8B-Reasoning-2512-Q8_0.gguf | Q8_0 | 9.03 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-Q8_0.gguf) |\n| Ministral-3-8B-Reasoning-2512-BF16-mmproj.gguf | BF16-mmproj | 858 MB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-8B-Reasoning-2512-BF16-mmproj.gguf) |\n\n## Ministral-3-3B-Reasoning-2512 [GGUF]\n\n| File Name | Quant Type | File Size | File Link |\n| - | - | - | - |\n| Ministral-3-3B-Reasoning-2512-BF16.gguf | BF16 | 6.87 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-BF16.gguf) |\n| Ministral-3-3B-Reasoning-2512-Q4_K_M.gguf | Q4_K_M | 2.15 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-Q4_K_M.gguf) |\n| Ministral-3-3B-Reasoning-2512-Q5_K_M.gguf | Q5_K_M | 2.47 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-Q5_K_M.gguf) |\n| Ministral-3-3B-Reasoning-2512-Q8_0.gguf | Q8_0 | 3.65 GB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-Q8_0.gguf) |\n| Ministral-3-3B-Reasoning-2512-BF16-mmproj.gguf | BF16-mmproj | 842 MB | [Download](https://huggingface.co/prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF/blob/main/Ministral-3-3B-Reasoning-2512-BF16-mmproj.gguf) |\n\n## Quants Usage \n\n(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)\n\nHere is a handy graph by ikawrakow comparing some lower-quality quant\ntypes (lower is better):\n\n![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "mistral3",
    "text-generation-inference",
    "llama.cpp",
    "f32",
    "image-text-to-text",
    "en",
    "fr",
    "es",
    "de",
    "it",
    "pt",
    "nl",
    "zh",
    "ja",
    "ko",
    "ar",
    "base_model:mistralai/Ministral-3-14B-Reasoning-2512",
    "base_model:quantized:mistralai/Ministral-3-14B-Reasoning-2512",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 88,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-03T16:29:41.000Z",
  "created_at": "2025-12-03T04:52:42.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": "transformers"
}

{
  "_id": "692fc21a5e5d56233ea0c9b4",
  "id": "prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF",
  "modelId": "prithivMLmods/Ministral-3-Reasoning-2512-AIO-GGUF",
  "sha": "1661748db831e3856c92b105c84a3d8d3d487306",
  "createdAt": "2025-12-03T04:52:42.000Z",
  "lastModified": "2025-12-03T16:29:41.000Z",
  "author": "prithivMLmods",
  "downloads": 88,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "transformers",
  "siblings_count": 18
}