Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16

RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16

Image Text to Text24B parametersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
3,677
Total downloads
510K
Gained 7D
Gained 30D
Likes
11
Rank · tracked models
#12,739
80(up 80 places)this week
Parameters
24B
Last source update
Aug 13, 2026
  • It moved from #1390 to #1383 among tracked Image Text to Text models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16 is a image text to text model published by RedHatAI. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 1h ago.

Published
Apr 15, 2025
Last updated
Aug 13, 2026
Library
License
apache-2.0
Task
Image Text to Text
Parameters
24,011,361,280
Spaces
Derivative models
Velocity 7D/day
safetensorsmistral3mistralaimistralmistral-smallneuralmagicredhatllmcompressorquantizedW4A16INT4conversational

Publisher

RedHatAIView publisher statistics →

Derived from mistralai/Mistral-Small-3.1-24B-Instruct-2503 (reported by the source; parent not yet tracked).

Similar models