#1 / TODAY
Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s
A Hacker News submission links to a GitHub repository, Niko1221/Strata, with a title claiming Qwen 3.8 Flash Next (125B) can run on consumer hardware, specifically an RTX 4090, at 100T/s. The published source text contains no repository README, benchmark methodology, or model details, only a GitHub feature-flag payload. The claim therefore rests on the submission title alone, with no supporting evidence in the excerpt.
The submission claims a 125B model runs on a single consumer GPU, but the source provides no benchmark details to verify it.
