GraySoft
Projects Models About FAQ Contact Download guIDE →

enlistedghost/magistral-small-2509-vision-gguf Q2_K_S GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.

Model Intelligence Sheet

enlistedghost/magistral-small-2509-vision-gguf overview

Comprehensive model page for enlistedghost/magistral-small-2509-vision-gguf

ggufMagistralVisionConversationalMultimodalImage-Text-to-TextGGUFGGMLQuantQuantizedLlama.cppOllamaMistralAI24Bimage-text-to-textenruukarxiv:2506.10910base_model:EnlistedGhost/Magistral-Small-2509-Visionbase_model:quantized:EnlistedGhost/Magistral-Small-2509-Visionlicense:apache-2.0endpoints_compatibleregion:usconversational
enlistedghost/magistral-small-2509-vision-gguf visual
Downloads
266
Likes
1
Pipeline
image-text-to-text
Library
Visibility
Public
Access
Open

Repository Files & Downloads

22 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
Magistral-Small-2509-Vision-BF16.gguf GGUF BF16 43.92 GB Download
Magistral-Small-2509-Vision-Q2_K.gguf GGUF Q2_K 8.59 GB Download
Magistral-Small-2509-Vision-Q2_K_L.gguf GGUF Q2_K_L 10.06 GB Download
Magistral-Small-2509-Vision-Q2_K_M.gguf GGUF Q2_K_M 8.89 GB Download
Magistral-Small-2509-Vision-Q2_K_S.gguf GGUF Q2_K_S 8.42 GB Download
Magistral-Small-2509-Vision-Q3_K_L.gguf GGUF Q3_K_L 11.23 GB Download
Magistral-Small-2509-Vision-Q3_K_M.gguf GGUF Q3_K_M 10.23 GB Download
Magistral-Small-2509-Vision-Q3_K_S.gguf GGUF Q3_K_S 9.93 GB Download
Magistral-Small-2509-Vision-Q3_K_XL.gguf GGUF Q3_K_XL 12.40 GB Download
Magistral-Small-2509-Vision-Q4_K_M.gguf GGUF Q4_K_M 12.78 GB Download
Magistral-Small-2509-Vision-Q4_K_S.gguf GGUF Q4_K_S 12.61 GB Download
Magistral-Small-2509-Vision-Q4_K_XL.gguf GGUF Q4_K_XL 13.81 GB Download
Magistral-Small-2509-Vision-Q5_K_M.gguf GGUF Q5_K_M 15.57 GB Download
Magistral-Small-2509-Vision-Q5_K_S.gguf GGUF Q5_K_S 15.27 GB Download
Magistral-Small-2509-Vision-Q5_K_XL.gguf GGUF Q5_K_XL 16.00 GB Download
Magistral-Small-2509-Vision-Q6_K.gguf GGUF Q6_K 18.02 GB Download
Magistral-Small-2509-Vision-Q6_K_M.gguf GGUF Q6_K_M 18.32 GB Download
Magistral-Small-2509-Vision-Q6_K_XL.gguf GGUF Q6_K_XL 19.49 GB Download
Magistral-Small-2509-Vision-Q8_0.gguf GGUF 23.33 GB Download
mmproj-Magistral-Small-2509-Vision-F16.gguf GGUF F16 837.38 MB Download
mmproj-Magistral-Small-2509-Vision-F32.gguf GGUF F32 1.64 GB Download
mmproj-Magistral-Small-2509-Vision-Q8_0.gguf GGUF 446.65 MB Download

Model Details Live

Model Slug
enlistedghost/magistral-small-2509-vision-gguf
Author
EnlistedGhost
Pipeline Task
image-text-to-text
Library
Created
2025-11-20
Last Modified
2025-12-17
Gated
No
Private
No
HF SHA
c1dbbc1568b36d645442ba6e0b2d5ed19b6fc11b
License
apache-2.0
Language
en, ru, uk
Base Model
EnlistedGhost/Magistral-Small-2509-Vision

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "license": "apache-2.0",
    "language": [
      "en",
      "ru",
      "uk"
    ],
    "base_model": [
      "EnlistedGhost/Magistral-Small-2509-Vision"
    ],
    "base_model_relation": "quantized",
    "new_version": "EnlistedGhost/Magistral-Small-2509-Vision-GGUF",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "Magistral",
      "Vision",
      "Conversational",
      "Multimodal",
      "Image-Text-to-Text",
      "GGUF",
      "GGML",
      "Quant",
      "Quantized",
      "Llama.cpp",
      "Ollama",
      "MistralAI",
      "24B"
    ],
    "frontmatter": {
      "license": "apache-2.0",
      "language": [
        "en",
        "ru",
        "uk"
      ],
      "base_model": [
        "EnlistedGhost/Magistral-Small-2509-Vision"
      ],
      "base_model_relation": "quantized",
      "new_version": "EnlistedGhost/Magistral-Small-2509-Vision-GGUF",
      "pipeline_tag": "image-text-to-text",
      "tags": [
        "Magistral",
        "Vision",
        "Conversational",
        "Multimodal",
        "Image-Text-to-Text",
        "GGUF",
        "GGML",
        "Quant",
        "Quantized",
        "Llama.cpp",
        "Ollama",
        "MistralAI",
        "24B"
      ]
    },
    "hero_image_url": "",
    "summary": "",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlicense: apache-2.0\nlanguage:\n- en\n- ru\n- uk\nbase_model:\n- EnlistedGhost/Magistral-Small-2509-Vision\nbase_model_relation: quantized\nnew_version: EnlistedGhost/Magistral-Small-2509-Vision-GGUF\npipeline_tag: image-text-to-text\ntags:\n- Magistral\n- Vision\n- Conversational\n- Multimodal\n- Image-Text-to-Text\n- GGUF\n- GGML\n- Quant\n- Quantized\n- Llama.cpp\n- Ollama\n- MistralAI\n- 24B\n---\n\n## -----------------------------------------------<br /> - Model Details and Specifications: -<br />-----------------------------------------------\n\n**Magistral-Small-2509-Vision (24B Parameters)**\n\n**Description:** <br />\nThis model was re-configured with MistralAI's original Magistral-Small vision tower,\nusing only official MistralAI files, weights and model data. This has resulted in a \nVision Multimodal version of Magistral-Small-2509 including fully functional Vision (re-enabled). <br /><br />\nThe Chat-template and System-prompt have been reworked and customized to improve\nperformance and quality across all Quantizated Files. No modifications, \nedits, or additional configurations are required to use this model with Ollama/Llama.cpp\nBoth Vision and Text work. (^.^) <br />\n\n**This release contains:** <br />\nLlama.cpp and Ollama compatible GGUF converted and Quantized model files <br />\n*(Compatible with both Ollama, and Llama.cpp)* <br />\n\n**IMPORTANT NOTICE as of **(GMT-8) 02:45 December 17th 2025**:** <br /> \nPlease note: The chat-template AND the system-prompt are custom and differ from what\nMistralAI made available. You can still use MistralAI's default template and prompt, but the model works very well\nusing what is provided within this release.\n<br /><br />\n\nHappy LLM Inferrencing,<br />\n-- Jon Z (EnlistedGhost)\n\n---------------------------------------------------\n\n## ---------------------------------------------------<br /> - Conversion and GGUF Quantization: -<br />---------------------------------------------------\n\n**Quantized GGUF version of:**\n- EnlistedGhost/Magistral-Small-2509-Vision <br /> *(by MistralAI - modified by EnlistedGhost)*\n\n**Original Model Link (Safetensors):**\n- [EnlistedGhost/Magistral-Small-2509-Vision](https://huggingface.co/EnlistedGhost/Magistral-Small-2509-Vision-GGUF)\n\n---------------------------------------------\n\n## -------------------------------<br /> ---- Updates & News ---- <br /> -------------------------------\n\n**Model Updates (as of: November 20th, 2025)**\n- Uploaded: GGUF Converted and Quantized model files\n- Created: ModelCard <br /> \n(this page)\n\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 | (Currently Uploading Files, Check again very 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 | [[mmproj Magistral-Small-2509-Vision Projector:Q8_0](https://huggingface.co/EnlistedGhost/Magistral-Small-2509-Vision-GGUF/resolve/main/mmproj-Magistral-Small-2509-Vision-Q8_0.gguf?download=true)]|\n| F16 | 870 MB | [[mmproj Magistral-Small-2509-Vision Projector:F16](https://huggingface.co/EnlistedGhost/Magistral-Small-2509-Vision-GGUF/resolve/main/mmproj-Magistral-Small-2509-Vision-F16.gguf?download=true)]|\n| F32 | 1.74 GB | [[mmproj Magistral-Small-2509-Vision Projector:F32](https://huggingface.co/EnlistedGhost/Magistral-Small-2509-Vision-GGUF/resolve/main/mmproj-Magistral-Small-2509-Vision-F32.gguf?download=true)]|\n\n\n-----------------------------------------------\n\n## -------------------------------------------------<br /> - Legal, Citations and Usage Details: -<br />-------------------------------------------------\n\n\n## Intended Use\nSame as original:\n- [[MistralAI](https://huggingface.co/mistralai/Magistral-Small-2509)]\n\n\n## Out-of-Scope Use\nSame as original:\n- [[MistralAI](https://huggingface.co/mistralai/Magistral-Small-2509)]\n\n\n## Bias, Risks, and Limitations\nSame as original:\n- [[MistralAI](https://huggingface.co/mistralai/Magistral-Small-2509)]\n\n\n## Evaluation\n- This model has NOT been evaluated in any form, scope or method of use. \n- **!!! USE AT YOUR OWN RISK !!!**\n- **!!! NO WARRANTY IS PROVIDED OF ANY KIND !!!**\n\n---------------------------------------------\n\n## Citation (Original Paper)\n[[MistalAI Magistral-Small-2509 Original Paper](https://huggingface.co/papers/2506.10910)]\n\n\n## Detailed Release Information\n- **Originally Developed by:** [[MistralAI](https://huggingface.co/mistralai/Magistral-Small-2509)]\n- **Modified with Vision re-Enabled by:** [[EnlistedGhost](https://huggingface.co/EnlistedGhost)]\n- **MMPROJ (Vision) Quantized by:** [[EnlistedGhost](https://huggingface.co/EnlistedGhost)]\n- **Model Quantized for GGUF by:** [[EnlistedGhost](https://huggingface.co/EnlistedGhost)]\n- **Model type & format:** [Quantized/GGUF]\n- **License type:** [Apache-2.0]\n\n## Model Card Authors and Contact\n[[EnlistedGhost](https://huggingface.co/EnlistedGhost)]",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "Magistral",
    "Vision",
    "Conversational",
    "Multimodal",
    "Image-Text-to-Text",
    "GGUF",
    "GGML",
    "Quant",
    "Quantized",
    "Llama.cpp",
    "Ollama",
    "MistralAI",
    "24B",
    "image-text-to-text",
    "en",
    "ru",
    "uk",
    "arxiv:2506.10910",
    "base_model:EnlistedGhost/Magistral-Small-2509-Vision",
    "base_model:quantized:EnlistedGhost/Magistral-Small-2509-Vision",
    "license:apache-2.0",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 266,
  "gated": false,
  "private": false,
  "last_modified": "2025-12-17T08:41:32.000Z",
  "created_at": "2025-11-20T10:36:27.000Z",
  "pipeline_tag": "image-text-to-text",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "691eef2be6fa75616f7be11b",
  "id": "EnlistedGhost/Magistral-Small-2509-Vision-GGUF",
  "modelId": "EnlistedGhost/Magistral-Small-2509-Vision-GGUF",
  "sha": "c1dbbc1568b36d645442ba6e0b2d5ed19b6fc11b",
  "createdAt": "2025-11-20T10:36:27.000Z",
  "lastModified": "2025-12-17T08:41:32.000Z",
  "author": "EnlistedGhost",
  "downloads": 266,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "image-text-to-text",
  "library_name": "",
  "siblings_count": 24
}