Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Mistral Small 24B Base2501

Model basics

Reasoning traces

Not supported

Context length

32K tokens

Max output length

No data

Model type

基础大模型

Release date

2025-01-30

Model file size

48GB

MoE architecture

Total params / Active params

240.0B / N/A

Knowledge cutoff

No data

Inference modes

No mode data

Mistral Small 24B Base2501

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- 免费商用授权

GitHub repo

GitHub link unavailable

Hugging Face

https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501

Live demo

No live demo

Mistral Small 24B Base2501

Official resources

Paper

Mistral Small 3 Apache 2.0, 81% MMLU, 150 tokens/s

DataLearnerAI blog

No blog post yet

Mistral Small 24B Base2501

API details

API speed

No data

No public API pricing yet.

Mistral Small 24B Base2501

Benchmark Results

No benchmark data to show.

Mistral Small 24B Base2501

Publisher

MistralAI

View publisher details

Mistral Small 3 - 24B

Model Overview

Mistral Small 3 是一款 24B 参数的模型，经过低延迟优化，并以 Apache 2.0 许可证发布。

本版本是其基座版本模型。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送