PrismML team fit a 27B model into 5.9 GB.
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
- dear rtx 3060 owners, and every 12gb card behind it. bonsai 2 27b dense went from 26 to… — @sudoingX
- Nice: banked codex reset for all of us. — @kimmonismus
- The #Mathematical #Programming - #FPGA. #BigData #Analytics #DataScience #AI… — @gp_pulipaka
- A Constraint Based Approach, ML. #BigData #Analytics #DataScience #AI #MachineLearning… — @gp_pulipaka
- Meet AliceAI-Foundation-80B-A3B-Base: a massive 80B parameter Mixture-of-Experts model… — @HuggingModels
- I am working on a new skill for Antigravity to prepare for Gemini 4, and I decided to… — @IamEmily2050
- There’s no way — @luckeyfaraday
- Cooked up a GLM-5.3-Flash-EXL3–2.32bpw for the 128GB crowd, perfect for your @NVIDIAAI… — @mr_r0b0t
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.