Mistralai Mistral Small 3.2 24B Instruct 2506 GGUF

🚀 Llamacpp imatrix Quantizations of Mistral-Small-3.2-24B-Instruct-2506 by mistralai

This project provides quantized versions of the Mistral-Small-3.2-24B-Instruct-2506 model, enabling efficient deployment on various hardware platforms.

🚀 Quick Start

• Run in LM Studio: You can run the quantized models in LM Studio.
• Run with llama.cpp: Run them directly with llama.cpp, or any other llama.cpp based project.

✨ Features

• Multi - language Support: Supports multiple languages including English, French, German, Spanish, Portuguese, Italian, Japanese, Korean, Russian, Chinese, Arabic, Farsi, Indonesian, Malay, Nepali, Polish, Romanian, Serbian, Swedish, Turkish, Ukrainian, Vietnamese, Hindi, and Bengali.
• Diverse Quantization Types: Offers a wide range of quantization types to balance between model quality and resource requirements.

📦 Installation

Install huggingface - cli

First, make sure you have hugginface - cli installed:

pip install -U "huggingface_hub[cli]"

Download a Specific File

Then, you can target the specific file you want:

huggingface-cli download bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF --include "mistralai_Mistral-Small-3.2-24B-Instruct-2506-Q4_K_M.gguf" --local-dir ./

Download Split Files

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/mistralai_Mistral-Small-3.2-24B-Instruct-2506-GGUF --include "mistralai_Mistral-Small-3.2-24B-Instruct-2506-Q8_0/*" --local-dir ./

You can either specify a new local - dir (mistralai_Mistral-Small-3.2-24B-Instruct-2506-Q8_0) or download them all in place (./)

💻 Usage Examples

Prompt format

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

📚 Documentation

What's new

• Fix chat template
• I know they updated the tool calling formatting, I attempted to recreate it but may have messed up, stay tuned for more updates if there's a better way

Download a file (not the whole branch)

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

ARM/AVX information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to this PR which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.

Which file should I choose?

🔧 Technical Details

Quantization Method

• Using llama.cpp release b5697 for quantization.
• All quants made using imatrix option with dataset from here

📄 License

This project is licensed under the apache - 2.0 license.

💡 Usage Tip

If you want to learn more about how we process your personal data, please read our Privacy Policy.

Credits

• Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
• Thank you ZeroWw for the inspiration to experiment with embed/output.
• Thank you to LM Studio for sponsoring my work.

Want to support my work? Visit my ko - fi page here: https://ko-fi.com/bartowski