umans/status/umans-flash
Live · refreshes every 30s
← all models
Umans Flash Fastest
umans-flash · Qwen3.6-35B-A3B · Qwen
also served as umans-qwen3.6-35b-a3b
Operational
258.3tok/s
throughput · p50
2.25s
TTFT · p50
99.58%
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
Trends

Speed over the last 90 days

daily medians · dashed line = target
throughput p50 · output tokens per second, higher is better
peak 401.0 tok/s · May 27now 289.2 tok/s
90 days agopre-release before May 3, 2026today
TTFT p50 · time to first token, lower is better
best 672ms · Jun 11now 1.05s
90 days agopre-release before May 3, 2026today
Changelog

Events for Umans Flash

incl. gateway-wide announcements
Jul 62026
Resolved: back to full capacity Resolved
Hardware capacity was restored and both umans-glm-5.2 and umans-kimi-k2.7 are back to normal speed. During the outage the service ran in a reduced-capacity mode that favoured continuity over speed: requests kept flowing, at the cost of an uneven experience. The affected window is shaded on each model's speed trends.
Jul 22026
Incident: hardware outage, running at reduced capacity Incident
A hardware failure took part of our GPU fleet offline. We failed over to reduced capacity to keep the service available: umans-glm-5.2 and umans-kimi-k2.7 stayed up, but slower than usual and with an uneven experience under load. Live updates were posted on Discord throughout.