A full-size open model now fits in 5.9 gigabytes.
PrismML released Bonsai 2 on 17 September, a squeezed copy of Alibaba's Qwen3.8 27B model. Every weight is stored as minus one, zero or plus one, shrinking the file ninefold. PrismML says it keeps 98.2% of the original's benchmark score, but nobody has rechecked that.
Why it mattersA model this size used to need a server, and it now runs on a gaming card. The weights carry an Apache licence, so you can download and run them freely.
▶ Related video: Is Bonsai 2 27B REALLY 98% of Qwen 3.8 27B fp16?
Read in the app — free, in 9 languages
Related stories
Alibaba's interpreter now translates you in your own voice.2026-09-20China Telecom's new open model fits on a gaming graphics card.
2026-09-20StepFun's new model matches one nearly five times its size.
2026-09-20A ChatGPT co-inventor raised $40m for a model that writes no text.
2026-09-19Alibaba opened up a model that spots 146 diseases in CT scans.
2026-09-19