I started testing local LLMs on real work. 2 repos, 105 planted bugs, find and fix what…
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.
I started testing local LLMs on real work. 2 repos, 105 planted bugs, find and fix what you can. A bug surprise was Qwen3.8-27B with 8-bit quantization. Opus 4.8 (max): 15 Qwen3.8-27B 8-bit: 10.7 Sonnet 5 (high): 9 Gemma 4 31B: 4 gpt-oss-120b: 0 (useless) This model is about 28.6 GB. For a 200K context window, you can comfortably run it on Mac mini 64 GB. Sure, it won't be as a genius like Fable or a hacker like GPT Astra, but you can use it to do some real, useful work. And the only cost would be electricity.
Posted by Paweł Huryn (130.9k followers) 2 days ago · 106 likes · 12.9k 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.