You can deploy this model and start earning money today!

tensorblock/
mlx-community_Magistral-Small-2506-bf16-GGUF

Name: mlx-community_Magistral-Small-2506-bf16-GGUF
Availability: InStock

mlx-community/Magistral-Small-2506-bf16

Views

No views yet

Website

Discord

GitHub

mlx-community/Magistral-Small-2506-bf16 - GGUF

Join our Discord to learn more about what we're building ↗

This repo contains GGUF format model files for mlx-community/Magistral-Small-2506-bf16.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b5753.

Our projects

Forge
Forge Project
An OpenAI-compatible multi-provider routing layer.
🚀 Try it now! 🚀
Awesome MCP Servers	TensorBlock Studio
MCP Servers	Studio
A comprehensive collection of Model Context Protocol (MCP) servers.	A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀	👀 See what we built 👀

Prompt template

<s>[SYSTEM_PROMPT]{system_prompt}[/SYSTEM_PROMPT][INST]{prompt}[/INST]

Model file specification

Filename	Quant type	File Size	Description
Magistral-Small-2506-bf16-Q2_K.gguf	Q2_K	8.890 GB	smallest, significant quality loss - not recommended for most purposes
Magistral-Small-2506-bf16-Q3_K_S.gguf	Q3_K_S	10.400 GB	very small, high quality loss
Magistral-Small-2506-bf16-Q3_K_M.gguf	Q3_K_M	11.474 GB	very small, high quality loss
Magistral-Small-2506-bf16-Q3_K_L.gguf	Q3_K_L	12.401 GB	small, substantial quality loss
Magistral-Small-2506-bf16-Q4_0.gguf	Q4_0	13.442 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Magistral-Small-2506-bf16-Q4_K_S.gguf	Q4_K_S	13.549 GB	small, greater quality loss
Magistral-Small-2506-bf16-Q4_K_M.gguf	Q4_K_M	14.334 GB	medium, balanced quality - recommended
Magistral-Small-2506-bf16-Q5_0.gguf	Q5_0	16.304 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Magistral-Small-2506-bf16-Q5_K_S.gguf	Q5_K_S	16.304 GB	large, low quality loss - recommended
Magistral-Small-2506-bf16-Q5_K_M.gguf	Q5_K_M	16.764 GB	large, very low quality loss - recommended
Magistral-Small-2506-bf16-Q6_K.gguf	Q6_K	19.346 GB	very large, extremely low quality loss
Magistral-Small-2506-bf16-Q8_0.gguf	Q8_0	25.055 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/mlx-community_Magistral-Small-2506-bf16-GGUF --include "Magistral-Small-2506-bf16-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/mlx-community_Magistral-Small-2506-bf16-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'