Auditing Strata: 125B on a 12 GB Card, 62 GB/s of RAM Bandwidth, and a 5× Contradiction in the Docs

Mon, 05 Oct 2026 00:00:00 +0000

Niko1221/Strata promises that a 125-billion-parameter model — Qwen3.8-Flash-Next — runs on your own gaming PC, that “a graphics card with 12 GB or more” is enough, and that it writes 94 tokens per second while doing it. It was created on 24 September 2026 and pushed to on 4 October, it reached the front page of Hacker News with 595 points and 279 comments, and it has 11,048 stars and 969 forks in 11 days.

The headline is the kind that usually collapses on contact. This one does not. I downloaded the repository, queried the GitHub API for the release, contributor and issue history, read the three documents that describe the engine, pulled the documentation’s own numbers apart, and did the memory-bandwidth arithmetic myself. The speed claim survives — but it survives for a reason the marketing sentence hides, and the same repository contradicts itself by a factor of 5.3 on prompt speed.

RAM Bandwidth on SoloSoft

Auditing Strata: 125B on a 12 GB Card, 62 GB/s of RAM Bandwidth, and a 5× Contradiction in the Docs