hugpadhugpad

ISTA-DASLab / Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g

Vision24B19.3K17Updated Apr 6, 2025
Hugging Face

Downloads

19.3K

Likes

17

Last updated

Apr 6, 2025

License

apache-2.0

This model was obtained by quantizing the weights of Mistral-Small-3.1-24B-Instruct-2503 to INT4 data type. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.

Tasks & library

  • image text to text
  • vllm

Tags

  • vllm
  • mistral3
  • int4
  • llmcompressor
  • image-text-to-text
  • conversational

Technical specifications

Parameters24B
Libraryvllm
LanguagesNot available
Base modelmistralai/Mistral-Small-3.1-24B-Instruct-2503
Licenseapache-2.0