Umans · Status · umans-glm-5.2-nvfp4

Umans GLM 5.2 NVFP4 Retired

umans-glm-5.2-nvfp4 · GLM

playground experiment; the test window ran Jun 29 to Jul 2, 2026

retired Jul 2, 2026 · replaced by umans-glm-5.2 · weights ↗

Retired

189.5tok/s

throughput · p50 · whole period

1.57s

TTFT · p50 · whole period

100.00%

uptime · whole period

Jun 27, 2026retired Jul 2, 2026Jul 4, 2026

Trends

Speed over its final 90 days

daily medians · dashed line = target

throughput p50 · output tokens per second, higher is better

peak 220.6 tok/s · Jun 30final 178.7 tok/s

Jun 27, 2026retired Jul 2, 2026Jul 4, 2026

TTFT p50 · time to first token, lower is better

best 1.27s · Jun 28final 1.44s

Jun 27, 2026retired Jul 2, 2026Jul 4, 2026

Changelog

incl. gateway-wide announcements

Jul 22026

Playground closed: Umans GLM 5.2 NVFP4 Testing

The short NVFP4 test window ended after four days. Thanks to everyone who pushed it and shared findings.

Jun 292026

Playground opened: Umans GLM 5.2 NVFP4 Testing

umans-glm-5.2-nvfp4 entered the playground for a short, low-capacity test window. Experimental and temporary; not for production.