Bonsai 2

Oct 9, 2026

Throughput

40.0 t/s gen

VRAM reported

12 GB

Summary

User reports Bonsai 2 running at 40 t/s and upwards on an RTX 3060 12GB. No engine, quant or context length is stated. The user says it is fast but gets stuck reasoning for hours for mediocre results, and asks for alternatives or tweaks.

View source ↗