hugpadhugpad

RedHatAI / Mistral-Small-24B-Instruct-2501-FP8-dynamic

Text Generation24B99.2K13Updated Jun 9, 2026
Hugging Face

Downloads

99.2K

Likes

13

Last updated

Jun 9, 2026

License

apache-2.0

Quantized version of Mistral-Small-24B-Instruct-2501. It achieves an average score of 78.88 on the OpenLLM benchmark (version 1), whereas the unquantized model achieves 79.45.

Tasks & library

  • text generation

Tags

  • mistral
  • mistral-small
  • fp8
  • vllm
  • conversational
  • compressed-tensors

Technical specifications

Parameters24B
LibraryNot available
Languages10 languages
Base modelmistralai/Mistral-Small-24B-Instruct-2501
Licenseapache-2.0