Umans Flash Fastest
also served as umans-qwen3.6-35b-a3b
343.2tok/s
throughput · p50 · last 5 min
596ms
TTFT · p50 · last 5 min
100.00%
uptime · 24h
Our fastest model: a light workflow complement, not a standalone coder. Think Haiku next to Opus: not everything needs a frontier model, and Flash's speed (200+ tokens per second) compounds on the roles around umans-coder: gathering context, scout subagents, research, summaries, documentation, and quick edits.
Context
262K
Max output
262K
Recommended
33K
Vision
Yes
Tools
Yes
Reasoning
Toggle · none/low/medium/high
Weights
Trends
Speed over the last 90 days
peak 372.1 tok/s · May 24now 249.9 tok/s
90 days agopre-release before May 3, 2026today
best 672ms · Jun 11now 869ms
90 days agopre-release before May 3, 2026today
Changelog
Events for Umans Flash
No recent events.