enlistedghost/ministral-3-3b-instruct-2512-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "datasets": [
      "mistralai/MM-MT-Bench"
    ],
    "language": [
      "en",
      "fr",
      "es",
      "de",
      "it",
      "pt",
      "nl",
      "zh",
      "ja",
      "ko",
      "ar"
    ],
    "base_model": [
      "mistralai/Ministral-3-3B-Instruct-2512-BF16"
    ],
    "new_version": "EnlistedGhost/Ministral-3-3B-Instruct-2512-GGUF",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "MistralAI",
      "Ministral",
      "Ministral-3",
      "Ollama",
      "Llama.cpp",
      "GGUF",
      "Image-Text-to-Text",
      "Conversational",
      "Quantize",
      "Multimodal",
      "Mistral3"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "datasets": [
        "mistralai/MM-MT-Bench"
      ],
      "language": [
        "en",
        "fr",
        "es",
        "de",
        "it",
        "pt",
        "nl",
        "zh",
        "ja",
        "ko",
        "ar"
      ],
      "base_model": [
        "mistralai/Ministral-3-3B-Instruct-2512-BF16"
      ],
      "new_version": "EnlistedGhost/Ministral-3-3B-Instruct-2512-GGUF",
      "pipeline_tag": "image-text-to-text",
      "tags": [
        "MistralAI",
        "Ministral",
        "Ministral-3",
        "Ollama",
        "Llama.cpp",
        "GGUF",
        "Image-Text-to-Text",
        "Conversational",
        "Quantize",
        "Multimodal",
        "Mistral3"
      ]
    },
    "hero_image_url": "https://ollama.com/assets/library/mistral-nemo/72045292-694a-4867-88c8-8635c9d97030",
    "summary": "**This release contains:**  Llama.cpp and Ollama compatible GGUF converted and Quantized model files *(Compatible with both Ollama, and Llama.cpp)* **Quantized GGUF version of:** **Original Model Link:** ----------------------------------------------",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\ndatasets:\n- mistralai/MM-MT-Bench\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-Instruct-2512-BF16\nnew_version: EnlistedGhost/Ministral-3-3B-Instruct-2512-GGUF\npipeline_tag: image-text-to-text\ntags:\n- MistralAI\n- Ministral\n- Ministral-3\n- Ollama\n- Llama.cpp\n- GGUF\n- Image-Text-to-Text\n- Conversational\n- Quantize\n- Multimodal\n- Mistral3\n---\n\n<img src=\"https://ollama.com/assets/library/mistral-nemo/72045292-694a-4867-88c8-8635c9d97030\" alt=\"Example image\" width=\"168\" height=\"128\"> \n\n\n<img src=\"https://ollama.com/assets/library/ministral-3/83fa3859-d87f-492c-bd81-596cfbceeccb\" alt=\"Example image\" width=\"64\" height=\"64\">\n\n## ------------------------------------------------<br /> - Model Details and Specifications: -<br />------------------------------------------------\n# Ministral-3 3B Instruct 2512 (GGUF)\n\n**This release contains:** <br />\nLlama.cpp and Ollama compatible GGUF converted and Quantized model files \n*(Compatible with both Ollama, and Llama.cpp)*\n\n**Quantized GGUF version of:**\n- Ministral-3-3B-Instruct-2512-BF16 <br /> *(by MistralAI)*\n\n**Original Model Link:**\n- [mistralai/Ministral-3-3B-Instruct-2512-BF16](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512-BF16)\n\n----------------------------------------------\n\n## -------------------------------------------------------------<br /> - GGUF Conversion and Quantization Details: -<br />-------------------------------------------------------------\n\n**Software used to convert Safetensors to GGUF:**\n- <a href=\"https://github.com/ggml-org/llama.cpp/\">llama.cpp</a>\n\n**Software used to create Quantized GGUF Files:**\n- <a href=\"https://github.com/ggml-org/llama.cpp/\">llama.cpp</a> \n\n**Specific GitHub Commit Point:**\n- <a href=\"https://github.com/ggml-org/llama.cpp/commit/85c40c9b02941ebf1add1469af75f1796d513ef4\">b7540</a>\n\n**Converted to GGUF and Quantized by:**\n- [EnlistedGhost](https://huggingface.co/EnlistedGhost)\n\n----------------------------------------------\n\n## --------------------------<br /> ---- Original Info ---- <br /> --------------------------\n*(Crossposted from the link in the above section: \"Model Details\"):*\n<br />\n<br />\n<br />\n<br />\n\n# Ministral 3 14B Instruct 2512 BF16\n\nThe largest model in the Ministral 3 family, **Ministral 3 14B** offers frontier capabilities and performance comparable to its larger [Mistral Small 3.2 24B](https://huggingface.co/mistralai/Mistral-Small-3.2-Instruct-2506) counterpart. A powerful and efficient language model with vision capabilities.\n\nThis model is the instruct post-trained version, fine-tuned for instruction tasks, making it ideal for chat and instruction based use cases.\n\nThe Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 14B can even be deployed locally, capable of fitting in 32GB of VRAM in BF16, and less than 24GB of RAM/VRAM when quantized.\n\nWe provide a no-loss FP8 version [here](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512), you can find other formats and quantizations in the [Ministral 3 - Additional Checkpoints](https://huggingface.co/collections/mistralai/ministral-3-additional-checkpoints) collection.\n\n## Key Features\nMinistral 3 14B consists of two main architectural components:\n- **13.5B Language Model**\n- **0.4B Vision Encoder**\n\nThe Ministral 3 14B Instruct model offers the following capabilities:\n- **Vision**: Enables the model to analyze images and provide insights based on visual content, in addition to text.\n- **Multilingual**: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.\n- **System Prompt**: Maintains strong adherence and support for system prompts.\n- **Agentic**: Offers best-in-class agentic capabilities with native function calling and JSON outputting.\n- **Edge-Optimized**: Delivers best-in-class performance at a small scale, deployable anywhere.\n- **Apache 2.0 License**: Open-source license allowing usage and modification for both commercial and non-commercial purposes.\n- **Large Context Window**: Supports a 256k context window.\n\n### Use Cases\nPrivate AI deployments where advanced capabilities meet practical hardware constraints:\n- Private/custom chat and AI assistant deployments in constrained environments\n- Advanced local agentic use cases\n- Fine-tuning and specialization\n- And more...\n  \nBringing advanced AI capabilities to most environments.\n\n## Ministral 3 Family\n\n| Model Name                     | Type               | Precision | Link                                                                                     |\n|--------------------------------|--------------------|-----------|------------------------------------------------------------------------------------------|\n| Ministral 3 3B Base 2512       | Base pre-trained   | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Base-2512)                |\n| **Ministral 3 3B Instruct 2512**   | **Instruct post-trained** | **BF16**   | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512)            |\n| Ministral 3 3B Reasoning 2512  | Reasoning capable  | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Reasoning-2512)           |\n| Ministral 3 8B Base 2512       | Base pre-trained   | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Base-2512)                |\n| Ministral 3 8B Instruct 2512   | Instruct post-trained | BF16    | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512)            |\n| Ministral 3 8B Reasoning 2512  | Reasoning capable  | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Reasoning-2512)           |\n| Ministral 3 14B Base 2512      | Base pre-trained   | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Base-2512)               |\n| Ministral 3 14B Instruct 2512  | Instruct post-trained | BF16    | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512)           |\n| Ministral 3 14B Reasoning 2512 | Reasoning capable  | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Reasoning-2512)          |\n\nOther formats available [here](https://huggingface.co/collections/mistralai/ministral-3-additional-checkpoints).\n\n## Benchmark Results\n\nWe compare Ministral 3 to similar sized models.\n\n### Reasoning\n\n| Model                     | AIME25      | AIME24      | GPQA Diamond | LiveCodeBench |\n|---------------------------|-------------|-------------|--------------|---------------|\n| **Ministral 3 14B**       | <u>0.850</u>| <u>0.898</u>| <u>0.712</u> | <u>0.646</u>  |\n| Qwen3-14B (Thinking)      | 0.737       | 0.837       | 0.663        | 0.593         |\n|                           |             |             |              |               |\n| **Ministral 3 8B**        | 0.787       | <u>0.860</u>| 0.668        | <u>0.616</u>  |\n| Qwen3-VL-8B-Thinking      | <u>0.798</u>| <u>0.860</u>| <u>0.671</u> | 0.580         |\n|                           |             |             |              |               |\n| **Ministral 3 3B**        | <u>0.721</u>| <u>0.775</u>| 0.534        | <u>0.548</u>  |\n| Qwen3-VL-4B-Thinking      | 0.697       | 0.729       | <u>0.601</u> | 0.513         |\n\n### Instruct\n\n| Model                     | Arena Hard  | WildBench  | MATH Maj@1  | MM MTBench       |\n|---------------------------|-------------|------------|-------------|------------------|\n| **Ministral 3 14B**       | <u>0.551</u>| <u>68.5</u>| <u>0.904</u>| <u>8.49</u>      |\n| Qwen3 14B (Non-Thinking)  | 0.427       | 65.1       | 0.870       | NOT MULTIMODAL   |\n| Gemma3-12B-Instruct       | 0.436       | 63.2       | 0.854       | 6.70             |\n|                           |             |            |             |                  |\n| **Ministral 3 8B**        | 0.509       | <u>66.8</u>| 0.876       | <u>8.08</u>      |\n| Qwen3-VL-8B-Instruct      | <u>0.528</u>| 66.3       | <u>0.946</u>| 8.00             |\n|                           |             |            |             |                  |\n| **Ministral 3 3B**        | 0.305       | <u>56.8</u>| 0.830       | 7.83             |\n| Qwen3-VL-4B-Instruct      | <u>0.438</u>| <u>56.8</u>| <u>0.900</u>| <u>8.01</u>      |\n| Qwen3-VL-2B-Instruct      | 0.163       | 42.2       | 0.786       | 6.36             |\n| Gemma3-4B-Instruct        | 0.318       | 49.1       | 0.759       | 5.23             |\n\n### Base\n\n| Model               | Multilingual MMLU | MATH CoT 2-Shot | AGIEval 5-shot | MMLU Redux 5-shot | MMLU 5-shot | TriviaQA 5-shot |\n|---------------------|-------------------|-----------------|----------------|-------------------|-------------|-----------------|\n| **Ministral 3 14B** | 0.742             | <u>0.676</u>    | 0.648          | 0.820             | 0.794       | 0.749           |\n| Qwen3 14B Base      | <u>0.754</u>      | 0.620           | <u>0.661</u>   | <u>0.837</u>      | <u>0.804</u>| 0.703           |\n| Gemma 3 12B Base    | 0.690             | 0.487           | 0.587          | 0.766             | 0.745       | <u>0.788</u>    |\n|                     |                   |                 |                |                   |             |                 |\n| **Ministral 3 8B**  | <u>0.706</u>      | <u>0.626</u>    | 0.591          | 0.793             | <u>0.761</u>| <u>0.681</u>    |\n| Qwen 3 8B Base      | 0.700             | 0.576           | <u>0.596</u>   | <u>0.794</u>      | 0.760       | 0.639           |\n|                     |                   |                 |                |                   |             |                 |\n| **Ministral 3 3B**  | 0.652             | <u>0.601</u>    | 0.511          | 0.735             | 0.707       | 0.592           |\n| Qwen 3 4B Base      | <u>0.677</u>      | 0.405           | <u>0.570</u>   | <u>0.759</u>      | <u>0.713</u>| 0.530           |\n| Gemma 3 4B Base     | 0.516             | 0.294           | 0.430          | 0.626             | 0.589       | <u>0.640</u>    |\n\n## License\n\nThis model is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0.txt).\n\n*You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.*",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "MistralAI",
    "Ministral",
    "Ministral-3",
    "Ollama",
    "Llama.cpp",
    "GGUF",
    "Image-Text-to-Text",
    "Conversational",
    "Quantize",
    "Multimodal",
    "Mistral3",
    "image-text-to-text",
    "en",
    "fr",
    "es",
    "de",
    "it",
    "pt",
    "nl",
    "zh",
    "ja",
    "ko",
    "ar",
    "dataset:mistralai/MM-MT-Bench",
    "base_model:mistralai/Ministral-3-3B-Instruct-2512-BF16",
    "base_model:quantized:mistralai/Ministral-3-3B-Instruct-2512-BF16",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 563,
  "gated": false,
  "private": false,
  "last_modified": "2026-01-16T21:18:16.000Z",
  "created_at": "2026-01-14T17:35:51.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": ""
}

{
  "_id": "6967d3f74efceeda711fba83",
  "id": "EnlistedGhost/Ministral-3-3B-Instruct-2512-GGUF",
  "modelId": "EnlistedGhost/Ministral-3-3B-Instruct-2512-GGUF",
  "sha": "4a2f5c4c1c7122bf33e347c0921994f40ee26138",
  "createdAt": "2026-01-14T17:35:51.000Z",
  "lastModified": "2026-01-16T21:18:16.000Z",
  "author": "EnlistedGhost",
  "downloads": 563,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "",
  "siblings_count": 28
}