enlistedghost/devstral-small-2507-vision-gguf overview

{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en",
      "ru",
      "uk",
      "de",
      "es",
      "pl",
      "sv",
      "ar",
      "tr",
      "be",
      "bn"
    ],
    "base_model": [
      "EnlistedGhost/Devstral-Small-2507-Vision"
    ],
    "new_version": "EnlistedGhost/Devstral-Small-2507-Vision-GGUF",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "Code",
      "Dev",
      "Devops",
      "Devstral",
      "Mistral",
      "MistralAI",
      "Image-Text-to-Text",
      "GGUF",
      "Quantized",
      "Ollama",
      "Llama.cpp",
      "Coding",
      "Vision"
    ],
    "datasets": [
      "mistralai/MM-MT-Bench"
    ],
    "library_name": "transformers",
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en",
        "ru",
        "uk",
        "de",
        "es",
        "pl",
        "sv",
        "ar",
        "tr",
        "be",
        "bn"
      ],
      "base_model": [
        "EnlistedGhost/Devstral-Small-2507-Vision"
      ],
      "new_version": "EnlistedGhost/Devstral-Small-2507-Vision-GGUF",
      "pipeline_tag": "image-text-to-text",
      "tags": [
        "Code",
        "Dev",
        "Devops",
        "Devstral",
        "Mistral",
        "MistralAI",
        "Image-Text-to-Text",
        "GGUF",
        "Quantized",
        "Ollama",
        "Llama.cpp",
        "Coding",
        "Vision"
      ],
      "datasets": [
        "mistralai/MM-MT-Bench"
      ],
      "library_name": "transformers"
    },
    "hero_image_url": "https://huggingface.co/api/resolve-cache/models/EnlistedGhost/Devstral-Small-2507-Vision-GGUF/f6b7c9d3bbd14eb5478c1d46df6f9beca2266d44/resources%2FScreenshot_20251227_232527.png?%2FEnlistedGhost%2FDevstral-Small-2507-Vision-GGUF%2Fresolve%2Fmain%2Fresources%2FScreenshot_20251227_232527.png",
    "summary": "**This release contains:**  Llama.cpp and Ollama compatible GGUF converted and Quantized model files *(Compatible with both Ollama, and Llama.cpp)*  *(More information and an updates to the ModelCard (this page) coming soon!)* **Quantized GGUF version of:** **Original Model Link:** ----------------------------------------------",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\n- ru\n- uk\n- de\n- es\n- pl\n- sv\n- ar\n- tr\n- be\n- bn\nbase_model:\n- EnlistedGhost/Devstral-Small-2507-Vision\nnew_version: EnlistedGhost/Devstral-Small-2507-Vision-GGUF\npipeline_tag: image-text-to-text\ntags:\n- Code\n- Dev\n- Devops\n- Devstral\n- Mistral\n- MistralAI\n- Image-Text-to-Text\n- GGUF\n- Quantized\n- Ollama\n- Llama.cpp\n- Coding\n- Vision\ndatasets:\n- mistralai/MM-MT-Bench\nlibrary_name: transformers\n---\n\n<img src=\"https://huggingface.co/api/resolve-cache/models/EnlistedGhost/Devstral-Small-2507-Vision-GGUF/f6b7c9d3bbd14eb5478c1d46df6f9beca2266d44/resources%2FScreenshot_20251227_232527.png?%2FEnlistedGhost%2FDevstral-Small-2507-Vision-GGUF%2Fresolve%2Fmain%2Fresources%2FScreenshot_20251227_232527.png\" alt=\"Devstral image\" width=\"285\" height=\"168\">\n\n## -----------------------------------------------<br /> - Model Details and Specifications: -<br />-----------------------------------------------\n\n# Devstral Small 2507 Vision GGUF (Ollama & Llama.cpp)\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)* <br />\n*(More information and an updates to the ModelCard (this page) coming soon!)*\n\n**Quantized GGUF version of:**\n- EnlistedGhost/Devstral-Small-2507-Vision <br /> *(by EnlistedGhost)*\n\n**Original Model Link:**\n- [EnlistedGhost/Devstral-Small-2507-Vision](https://huggingface.co/EnlistedGhost/Devstral-Small-2507-Vision)\n\n----------------------------------------------\n\n## ---------------------------------------------------<br /> - Conversion and GGUF Quantization: -<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=\"#\">b7266</a>\n\n**Converted to GGUF and Quantized by:**\n- [EnlistedGhost](https://huggingface.co/EnlistedGhost)\n\n----------------------------------------------\n\n## -------------------------------<br /> ---- Updates & News ---- <br /> -------------------------------\n\n**Model Updates (as of: December 28th, 2025)**\n- Uploaded: All remaining GGUF Converted and Quantized model files (Q5_K, Q6_K, Q8_0)\n- Updated: ModelCard <br /> \n(this page)\n\n---------------------------------------------\n\n### --------------------------------------<br /> ---- How to run this Model ---- <br /> --------------------------------------\n\n**Compatible Software (Required to use this Model**) <br />\nYou can run this model by using either Ollama (or) Llama.cpp <br />\n*(Below are instruction on running these GGUF files with Ollama)*\n\n**How to run this Model using Ollama** <br />\nYou can run this model by using the \"ollama run\" command.<br />\nSimply copy & paste one of the commands from the list below into<br /> \nyour console, terminal or power-shell window.\n| Quant Type | File Size | Command |\n|:-----------|:----------|:--------|\n| QX_X | 0.00 GB | Run/Pull Command (Coming Soon) |\n\n**Vision Projector (Files)** <br />\n*mmproj (Vision Projector) Files*\n| Quant Type | File Size | Download Link |\n|:-----------|:----------|:--------|\n| Q8_0 | 465 MB | |\n| F16 | 870 MB | |\n| F32 | 1.74 GB | |\n\n\n-----------------------------------------------\n\n\n## ---------------------------<br /> ---- Original Info ---- <br /> ---------------------------\n*(Crossposted from the link in the above section: \"Model Details\"):*\n<br />\n<br />\n\n# Devstral Small 1.1\n\nDevstral is an agentic LLM for software engineering tasks built under a collaboration between [Mistral AI](https://mistral.ai/) and [All Hands AI](https://www.all-hands.dev/) 🙌. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench which positions it as the #1 open source model on this [benchmark](#benchmark-results). \n\nIt is finetuned from [Mistral-Small-3.1](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503), therefore it has a long context window of up to 128k tokens. As a coding agent, Devstral is text-only and before fine-tuning from `Mistral-Small-3.1` the vision encoder was removed.\n\nFor enterprises requiring specialized capabilities (increased context, domain-specific knowledge, etc.), we will release commercial models beyond what Mistral AI contributes to the community.\n\nLearn more about Devstral in our [blog post](https://mistral.ai/news/devstral-2507).\n\n**Updates compared to [`Devstral Small 1.0`](https://huggingface.co/mistralai/Devstral-Small-2505):**\n- Improved performance, please refer to the [benchmark results](#benchmark-results).\n- `Devstral Small 1.1` is still great when paired with OpenHands. This new version also generalizes better to other prompts and coding environments. \n- Supports [Mistral's function calling format](https://mistralai.github.io/mistral-common/usage/tools/).\n\n\n## Key Features:\n- **Agentic coding**: Devstral is designed to excel at agentic coding tasks, making it a great choice for software engineering agents.\n- **lightweight**: with its compact size of just 24 billion parameters, Devstral is light enough to run on a single RTX 4090 or a Mac with 32GB RAM, making it an appropriate model for local deployment and on-device use.\n- **Apache 2.0 License**: Open license allowing usage and modification for both commercial and non-commercial purposes.\n- **Context Window**: A 128k context window.\n- **Tokenizer**: Utilizes a Tekken tokenizer with a 131k vocabulary size.\n\n\n## Benchmark Results\n\n### SWE-Bench\n\nDevstral Small 1.1 achieves a score of **53.6%** on SWE-Bench Verified, outperforming Devstral Small 1.0 by +6,8% and the second best state of the art model by +11.4%.\n\n| Model              | Agentic Scaffold   | SWE-Bench Verified (%) |\n|--------------------|--------------------|------------------------|\n| Devstral Small 1.1 | OpenHands Scaffold | **53.6**               |\n| Devstral Small 1.0 | OpenHands Scaffold | *46.8*                 |\n| GPT-4.1-mini       | OpenAI Scaffold    | 23.6                   |\n| Claude 3.5 Haiku   | Anthropic Scaffold | 40.6                   |\n| SWE-smith-LM 32B   | SWE-agent Scaffold | 40.2                   |\n| Skywork SWE        | OpenHands Scaffold | 38.0                   |\n| DeepSWE            | R2E-Gym   Scaffold | 42.2                   |\n\n\n When evaluated under the same test scaffold (OpenHands, provided by All Hands AI 🙌), Devstral exceeds far larger models such as Deepseek-V3-0324 and Qwen3 232B-A22B.\n\n![SWE Benchmark](assets/swe_benchmark.png)\n\n## Usage\n\nWe recommend to use Devstral with the [OpenHands](https://github.com/All-Hands-AI/OpenHands/tree/main) scaffold.\nYou can use it either through our API or by running locally.",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "Code",
    "Dev",
    "Devops",
    "Devstral",
    "Mistral",
    "MistralAI",
    "Image-Text-to-Text",
    "GGUF",
    "Quantized",
    "Ollama",
    "Llama.cpp",
    "Coding",
    "Vision",
    "image-text-to-text",
    "en",
    "ru",
    "uk",
    "de",
    "es",
    "pl",
    "sv",
    "ar",
    "tr",
    "be",
    "bn",
    "dataset:mistralai/MM-MT-Bench",
    "base_model:EnlistedGhost/Devstral-Small-2507-Vision",
    "base_model:quantized:EnlistedGhost/Devstral-Small-2507-Vision",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 2,
  "downloads": 460,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-28T10:26:38.000Z",
  "created_at": "2025-12-08T10:16:24.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": "transformers"
}

{
  "_id": "6936a578329352fc31ec4a30",
  "id": "EnlistedGhost/Devstral-Small-2507-Vision-GGUF",
  "modelId": "EnlistedGhost/Devstral-Small-2507-Vision-GGUF",
  "sha": "e1152f13f24c9c7f48a8e5606f9f9d53099d8392",
  "createdAt": "2025-12-08T10:16:24.000Z",
  "lastModified": "2025-12-28T10:26:38.000Z",
  "author": "EnlistedGhost",
  "downloads": 460,
  "likes": 2,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "transformers",
  "siblings_count": 27
}