Instructions to use EnlistedGhost/Magistral-Small-2509-Vision-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EnlistedGhost/Magistral-Small-2509-Vision-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="EnlistedGhost/Magistral-Small-2509-Vision-GGUF",
	filename="Magistral-Small-2509-Vision-BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use EnlistedGhost/Magistral-Small-2509-Vision-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M

Use Docker

docker model run hf.co/EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use EnlistedGhost/Magistral-Small-2509-Vision-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EnlistedGhost/Magistral-Small-2509-Vision-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EnlistedGhost/Magistral-Small-2509-Vision-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M

Ollama
How to use EnlistedGhost/Magistral-Small-2509-Vision-GGUF with Ollama:
```
ollama run hf.co/EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M
```

Unsloth Studio new

How to use EnlistedGhost/Magistral-Small-2509-Vision-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for EnlistedGhost/Magistral-Small-2509-Vision-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for EnlistedGhost/Magistral-Small-2509-Vision-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EnlistedGhost/Magistral-Small-2509-Vision-GGUF to start chatting

Docker Model Runner
How to use EnlistedGhost/Magistral-Small-2509-Vision-GGUF with Docker Model Runner:
```
docker model run hf.co/EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M
```

Lemonade

How to use EnlistedGhost/Magistral-Small-2509-Vision-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EnlistedGhost/Magistral-Small-2509-Vision-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Magistral-Small-2509-Vision-GGUF-Q4_K_M

List all available models

lemonade list

-----------------------------------------------
- Model Details and Specifications: -
-----------------------------------------------

Magistral-Small-2509-Vision (24B Parameters)

Description:
This model was re-configured with MistralAI's original Magistral-Small vision tower, using only official MistralAI files, weights and model data. This has resulted in a Vision Multimodal version of Magistral-Small-2509 including fully functional Vision (re-enabled).

The Chat-template and System-prompt have been reworked and customized to improve performance and quality across all Quantizated Files. No modifications, edits, or additional configurations are required to use this model with Ollama/Llama.cpp Both Vision and Text work. (^.^)

This release contains:
Llama.cpp and Ollama compatible GGUF converted and Quantized model files
(Compatible with both Ollama, and Llama.cpp)

IMPORTANT NOTICE as of (GMT-8) 02:45 December 17th 2025:
Please note: The chat-template AND the system-prompt are custom and differ from what MistralAI made available. You can still use MistralAI's default template and prompt, but the model works very well using what is provided within this release.

Happy LLM Inferrencing,
-- Jon Z (EnlistedGhost)

---------------------------------------------------
- Conversion and GGUF Quantization: -
---------------------------------------------------

Quantized GGUF version of:

EnlistedGhost/Magistral-Small-2509-Vision
(by MistralAI - modified by EnlistedGhost)

Original Model Link (Safetensors):

EnlistedGhost/Magistral-Small-2509-Vision

-------------------------------
---- Updates & News ----
-------------------------------

Model Updates (as of: November 20th, 2025)

Uploaded: GGUF Converted and Quantized model files
Created: ModelCard
(this page)

--------------------------------------
---- How to run this Model ----
--------------------------------------

Compatible Software (Required to use this Model)
You can run this model by using either Ollama (or) Llama.cpp
(Below are instruction on running these GGUF files with Ollama)

How to run this Model using Ollama
You can run this model by using the "ollama run" command.
Simply copy & paste one of the commands from the list below into
your console, terminal or power-shell window.

Quant Type	File Size	Command
QX_X	0.00 GB	(Currently Uploading Files, Check again very soon!)

Vision Projector (Files)
mmproj (Vision Projector) Files

Quant Type	File Size	Download Link
Q8_0	465 MB	[mmproj Magistral-Small-2509-Vision Projector:Q8_0]
F16	870 MB	[mmproj Magistral-Small-2509-Vision Projector:F16]
F32	1.74 GB	[mmproj Magistral-Small-2509-Vision Projector:F32]

-------------------------------------------------
- Legal, Citations and Usage Details: -
-------------------------------------------------

Intended Use

Same as original:

[MistralAI]

Out-of-Scope Use

Same as original:

[MistralAI]

Bias, Risks, and Limitations

Same as original:

[MistralAI]

Evaluation

This model has NOT been evaluated in any form, scope or method of use.
!!! USE AT YOUR OWN RISK !!!
!!! NO WARRANTY IS PROVIDED OF ANY KIND !!!

Citation (Original Paper)

[MistalAI Magistral-Small-2509 Original Paper]

Detailed Release Information

Originally Developed by: [MistralAI]
Modified with Vision re-Enabled by: [EnlistedGhost]
MMPROJ (Vision) Quantized by: [EnlistedGhost]
Model Quantized for GGUF by: [EnlistedGhost]
Model type & format: [Quantized/GGUF]
License type: [Apache-2.0]

Model Card Authors and Contact

[EnlistedGhost]

Downloads last month: 806

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for EnlistedGhost/Magistral-Small-2509-Vision-GGUF

Base model

mistralai/Mistral-Small-3.1-24B-Base-2503

Finetuned

mistralai/Mistral-Small-3.2-24B-Instruct-2506

Finetuned

EnlistedGhost/Magistral-Small-2509-Vision

Quantized

(3)

this model

Paper for EnlistedGhost/Magistral-Small-2509-Vision-GGUF

Magistral

Paper • 2506.10910 • Published Jun 12, 2025 • 68

----------------------------------------------- - Model Details and Specifications: ------------------------------------------------

--------------------------------------------------- - Conversion and GGUF Quantization: ----------------------------------------------------

------------------------------- ---- Updates & News ---- -------------------------------

-------------------------------------- ---- How to run this Model ---- --------------------------------------

------------------------------------------------- - Legal, Citations and Usage Details: --------------------------------------------------

Intended Use

Out-of-Scope Use

Bias, Risks, and Limitations

Evaluation

Citation (Original Paper)

Detailed Release Information

Model Card Authors and Contact

Model tree for EnlistedGhost/Magistral-Small-2509-Vision-GGUF

Paper for EnlistedGhost/Magistral-Small-2509-Vision-GGUF

-----------------------------------------------
- Model Details and Specifications: -
-----------------------------------------------

---------------------------------------------------
- Conversion and GGUF Quantization: -
---------------------------------------------------

-------------------------------
---- Updates & News ----
-------------------------------

--------------------------------------
---- How to run this Model ----
--------------------------------------

-------------------------------------------------
- Legal, Citations and Usage Details: -
-------------------------------------------------