mistralai/mistral-inference
Official inference library for Mistral models
This is a tool for developers who want to run Mistral's large language models (LLMs) on their own hardware. It allows you to take pre-trained Mistral models and process text or code inputs to generate text, code, or other relevant outputs. It's used by machine learning engineers or AI practitioners looking to integrate Mistral models into their applications or research.
10,705 stars.
Use this if you are an AI developer looking to locally deploy and experiment with Mistral's range of open-weight large language models for various text generation or coding tasks.
Not ideal if you are an end-user without programming knowledge or if you prefer a ready-to-use application rather than deploying models yourself.
Stars
10,705
Forks
1,024
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mistralai/mistral-inference"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Community Discussion
Recent Releases
Related models
dvmazur/mixtral-offloading
Run Mixtral-8x7B models in Colab or consumer desktops
open-compass/MixtralKit
A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
vicuna-tools/vicuna-installation-guide
The "vicuna-installation-guide" provides step-by-step instructions for installing and...
pleisto/yuren-13b
Yuren 13B is an information synthesis large language model that has been continuously trained...
hkproj/mistral-llm-notes
Notes on the Mistral AI model