Mistral: Mistral Small 3.1 24B

Made by mistralai. Open weights

Input price
$0.351
per 1M tokens
Output price
$0.555
per 1M tokens
Context window
128K
tokens
Quality
1,278
#272 on LMArena
Size
24B
parameters
Downloads
428.8K
on Hugging Face, last 30 days

Can I run it locally?

Estimate for the Q4_K_M version with an 8K context. Pick your own card and settings in the calculator.

  • NVIDIA GeForce RTX 40608 GBRuns, but slowly3.9 to 5.5 tokens/s
  • NVIDIA GeForce RTX 306012 GBRuns, but slowly6.5 to 9.3 tokens/s
  • NVIDIA GeForce RTX 4060 Ti 16 GB16 GBRuns12 to 17 tokens/s
  • NVIDIA GeForce RTX 409024 GBRuns41 to 58 tokens/s
  • NVIDIA GeForce RTX 509032 GBRuns73 to 104 tokens/s
  • Apple M1 Pro 32 GB32 GBRuns8.2 to 12 tokens/s
Check my computer

Prices: OpenRouter, refreshed 9 Oct 2026. Quality: LMArena (CC BY 4.0), leaderboard of 2 Oct 2026. Model page on Hugging Face