Dev Radar
Support
LiveUpdated 2026-09-19 18:39 UTC

PrismML team fit a 27B model into 5.9 GB.

PrismML team fit a 27B model into 5.9 GB. We uncensored it without changing a single weight. 🐳 Introducing OrcaRouter…

This is a dev post classified by Jev as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.

PrismML team fit a 27B model into 5.9 GB. We uncensored it without changing a single weight. 🐳 Introducing OrcaRouter Ternary Bonsai 2 27B Uncensored. Traditional abliteration modifies weights. On a ~1.72-bit ternary model, that means re-quantization — potentially destroying the quality preserved by QAT. So we moved abliteration into the runtime. → 0 weights modified → 0 re-quantization → original 5.9 GB pack stays bit-identical → 129 residual intervention sites → adjustable at inference → runs locally on Apple Silicon No modified checkpoint. Bring the original Bonsai pack + our runtime.

Posted by OrcaRouter 🐳 (19.9k followers) 1 days ago · 3.9k likes · 295.6k views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: orcabonsai-27b-uncensored.

More dev work like this

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:39 UTC. Full method.