Umans Kimi K2.5 Retired
retired May 13, 2026 · replaced by umans-kimi-k2.6 · weights ↗
46.6tok/s
throughput · p50 · whole period
2.91s
TTFT · p50 · whole period
100.00%
uptime · whole period
Trends
Speed over its final 90 days
peak 158.6 tok/s · May 11final 66.7 tok/s
Feb 14, 2026retired May 13, 2026May 15, 2026
best 1.49s · Apr 27final 3.00s
Feb 14, 2026retired May 13, 2026May 15, 2026
Changelog
Events for Umans Kimi K2.5
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.
May 132026
Retired: Umans Kimi K2.5 Retired
umans-kimi-k2.5 was retired and superseded by Kimi K2.6.