the most owned gpu on steam is a five year old rtx 3060 12gb vram. today in 2026 that…
This is a AI post classified by Jev as Open & local models (a tool drop), kept by the AI Radar because it carries real work, not commentary.
the most owned gpu on steam is a five year old rtx 3060 12gb vram. today in 2026 that card runs a qwen 3.8 27b dense: > 26 tok/s on prismml's stock fork > 40 tok/s with my kernel fix, same file > 50 tok/s with the mtp head grafted back, lossless, the words do not change (releasing) > 262k context resident, 11.7 of 12 gb > 77 minutes of agentic build done with one prompt, a working file all measured on one rtx 3060 12gb. the repo has the serve line for every vram tier and the tools, open for anyone. bookmark this if you own a 12gb card, the row for your card is one clone away, and if you get
Posted by Sudo su (36.3k followers) 1 h ago · 1 likes · 789 views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: bonsai2-small-gpu.
More AI work like this
- Laya is the open-source Jev that already beats close Jev on latency and calibration. — @0x0SojalSec
- Leak: DeepSeek V5 incoming Claim: beats Astra, matches Fable 5.1, stays open-weight,… — @0x0SojalSec
- Qwen 3.8 Flash Next locally is actually blowing my mind!! — @loktar00
- @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
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. 31.7k posts from 4.8k X accounts over the last 14 days, 1.3k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 04:05 UTC. Full method.