Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.

874 12 days ago

Readme

From huggingface: https://huggingface.co/mrfakename/mistral-small-3.1-24b-instruct-2503-gguf

Only the text component has been converted to GGUF, does not work as a vision model.