your gaming gpu can run a 27 billion parameter model at home, free, no account, nothing…
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.
your gaming gpu can run a 27 billion parameter model at home, free, no account, nothing leaving the machine, and since tonight it runs at twice the speed it did yesterday. i went into the code that serves it, found the kernel leaving two thirds of the card's threads idle on the biggest matrices, fixed that, then grafted the draft head back on top. 25 tok/s stock, 50 tok/s now, on an rtx 3060, a card people bought to play games. it writes faster than you can read it, it holds a 262k context window, and it is a 7 gb download. 3060, 3070, 4060, 4070, 4080, 4090, 8gb and up, it is yours tonight
Posted by Sudo su (36.3k followers) 3 h ago · 29 likes · 3k views · view the original post on X. Kept by the AI Radar as Open & local models. Tools mentioned: ternary-bonsai-2-27b-ptq1_0-mtp-gguf.
More AI work like this
- One of the coolest local AI experiences I’ve tried on iPhone. — @pratikg
- In the AI era, information moves fast. Staying current matters. — @OpenBMB
- Easiest way to start with Local AI in 2026 — @TheAhmadOsman
- Qwen-image-2.1 text rendering examples — @ItsmeAjayKV
- Update: next checkpoint has effectively reached Jev calibration parity on MMLU! Also 8… — @4rcherhume
- Updated checkpoint coming soon. Much better calibration across text and image w/ better… — @4rcherhume
- ok I had to try: same demo, open model. — @victormustar
- This looks... interesting 👀 — @MiaAI_lab
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. 38.9k posts from 5k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 15:58 UTC. Full method.