Local models are getting remarkably compact.
This is a AI post classified by Jev as Open & local models (a model release), kept by the AI Radar because it carries real work, not commentary.
Local models are getting remarkably compact. PrismML has released Bonsai 2 27B, based on Qwen3.8 27B. With three-digit quantization, it takes just 5.9 GB — roughly 9× smaller than the full version. Developer tests show it retains 98.2% of the original score, while supporting image input and tool calling. It’s also open under Apache 2.0. How far can this push capable local AI onto everyday hardware?
Posted by David Arnal (1.5k followers) 1 days ago · 2 likes · 240 views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- @Da7_Tech — @Da7_Tech
- Some AI labs are trying to get local models banned — @AlexFinn
- You can run locally Uncensored Ternary Bonsai 2-27B Same 5.9GB file. — @0x0SojalSec
- Most local models still sound like customer support. — @0x0SojalSec
- I'm done with Bonsai 2 27B. This model has taken enough of my time and patience. — @superalesha
- dear rtx 3060 owners, and every 12gb card behind it. bonsai 2 27b dense went from 26 to… — @sudoingX
- Nimble is able to process images! — @madiator
- Woah...it claims to be open Jev. And it's 100% opensource. — @Saboo_Shubham_
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. 31.3k posts from 4.7k X accounts over the last 14 days, 1.3k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 21:10 UTC. Full method.