Qwen3.8 Flash-Next as a Labs experiment, open for a short test window: temporary, not a permanent id. Served from Qwen's official FP8 checkpoint: a 125B mixture-of-experts model with 6B active parameters per token, the first open release of the next-generation architecture that powers the upcoming Qwen4 family, with native image and video understanding, built for fast coding and agentic tasks on a 256K context window. It thinks by default at xhigh effort; reasoning can be tuned down (low, medium) or turned off (none). Access is seat-gated through the Labs page while an experiment is live. It is offered at limited capacity and low availability, so expect it to be flaky and to go down under load: crash it, give it a moment, and try again. For production work we recommend umans-coder or umans-deepseek-v4-pro-0813.
Umans Qwen3.8 Flash Next (lab) Playground Retired
playground experiment; the Qwen3.8 Flash-Next lab window ran Aug 27 to 28, 2026
retired Aug 28, 2026 · weights ↗
143.6tok/s
throughput · p50 · whole period
2.81s
TTFT · p50 · whole period
0.00%
uptime · whole period
Trends
final 159.1 tok/s
Aug 27, 2026retired Aug 28, 2026Aug 30, 2026
final 2.69s
Aug 27, 2026retired Aug 28, 2026Aug 30, 2026
Changelog
Aug 282026
Playground closed: Umans Qwen3.8 Flash Next Testing
The Qwen3.8 Flash-Next lab window closed on August 28, 2026 (opened early on August 27 and extended past the announced close). Thanks to everyone who pushed it - text, images, and the xhigh thinking dial - and shared findings. The experiment answered its framing question and the model does not earn a permanent slot right now: umans-qwen3.8-flash-next-lab is retired to the past-models list, and there is no successor id. For production work we recommend umans-coder or umans-deepseek-v4-pro-0813.
Aug 262026
New Labs experiment: Umans Qwen3.8 Flash Next Testing
A new lab opened on umans-qwen3.8-flash-next-lab: Qwen3.8 Flash-Next served from Qwen's official FP8 checkpoint, a 125B mixture-of-experts model (6B active per token) and the first open release of the next-generation architecture that powers the upcoming Qwen4 family, with native image understanding and a 256K context window, thinking at xhigh effort by default (dial to low or medium, or turn thinking off). Free and seat-gated while the experiment runs, served at limited capacity and low availability: it is a lab, so expect it to be flaky and to go down under load. Crash it, give it a moment, and try again. The window closes August 27, 2026.