Unsloth Runs a 2-Bit Quantized 35B Model That Completes Full Repo Bug Hunts in 13GB of RAM

A heavily quantized Qwen model performed evidence gathering, reproduction, fixes, tests, and PR writeups for real repository bugs — all running locally.

Unsloth demonstrated a 2-bit quantized version of Qwen3.6-35B-A3B completing a full repository bug hunt workflow, including evidence collection, reproduction steps, code fixes, test generation, and a pull request writeup, all running locally in Unsloth Studio with just 13GB of RAM, as @UnslothAI showed.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief