Umans · Status · umans-flash

← all models

Umans Flash Fastest

umans-flash · Qwen3.6-35B-A3B · Qwen

also served as umans-qwen3.6-35b-a3b

Operational

336.1tok/s

throughput · p50 · last 5 min

1.14s

TTFT · p50 · last 5 min

99.83%

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.

90 days agoin production since May 3, 2026today

Context

262K

Max output

262K

Recommended

33K

Vision

Yes

Tools

Yes

Reasoning

Toggle · none/low/medium/high

Weights

FP8 ↗

Trends

Speed over the last 90 days

daily medians · dashed line = target

throughput p50 · output tokens per second, higher is better

peak 372.1 tok/s · May 24now 336.7 tok/s

90 days agopre-release before May 3, 2026today

TTFT p50 · time to first token, lower is better

best 672ms · Jun 11now 839ms

90 days agopre-release before May 3, 2026today

Changelog

Events for Umans Flash

incl. gateway-wide announcements

No recent events.