MiniMax-M3.1-Flash-pruned-285B-NVFP4

primitive-ai/MiniMax-M3.1-Flash-pruned-285B-NVFP4

Image Text to Text149B parametersvllmLicense: other
Tracked by OpenModelStats since October 31, 2026View on Hugging Face ↗
Downloads 30D
527
Total downloads
527
Gained 7D
—
Gained 30D
—
Likes
6
Rank · tracked models
#54,396
3795(up 3795 places)this week
Parameters
149B
Last source update
Oct 31, 2026
  • It moved from #5514 to #5253 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

MiniMax-M3.1-Flash-pruned-285B-NVFP4 is a image text to text model published by primitive-ai. OpenModelStats has tracked the model since Oct 31, 2026, most recently observing it 5h ago.

Published
Oct 23, 2026
Last updated
Oct 31, 2026
Library
vllm
License
other
Task
Image Text to Text
Parameters
149,470,069,940
Spaces
—
Derivative models
—
Velocity 7D/day
—
vllmsafetensorsminimax_m3_vlcompressed-tensorsnvfp4moeexpert-pruningminimax-m3reasoningagentictool-callingimage-text-to-text

Publisher

primitive-aiView publisher statistics →

Derived from MiniMaxAI/MiniMax-M3.1-Flash (reported by the source; parent not yet tracked).

Similar models

Models similar to MiniMax-M3.1-Flash-pruned-285B-NVFP4
ModelDL 30D
Qwen3.8-Flash-Next-REAP-384-MLX-4bitsh0wie1,402
GLM5.3-Flash-E256-DGX-Sparkautotrust7,586
DeepSeek-V4.1-Flash-1017-EXL3-4.0bpwbertholomus475
Qwen3.8-Flash-Next-E384-FP4-V2autotrust72.9K
Qwen3.8-Flash-Next-E384-FP4-Localautotrust62.7K
Inkling-Small-NVFP4thinkingmachines82.4K