AI Radar
Support
LiveUpdated 2026-09-19 18:08 UTC

LocalMaxxing

LocalMaxxing — Qwen3.8-27B achieved 90.8 tok/s output speed on Radeon AI Pro R9700 · 32 GB ×3 using…

LocalMaxxing is Qwen3.8-27B achieved 90.8 tok/s output speed on Radeon AI Pro R9700 · 32 GB ×3 using llama.cpp · Q8_0. See the full benchmark on LocalMaxxing.. It is ranked #374 on the AI Radar, in Open & local models, first seen 13 days ago and shared in 4 posts (22.9k views).

Visit localmaxxing.com

What people said about LocalMaxxing on X

We making this work w/ tenstorrent P150 TP2 soon, dflash2 soon, qwen 27b soon Better quants soon Will be sharing everything https://www.localmaxxing.com/en/models/Lottolabs/Qwen3.5-9B-TT-BFP4-P150?run=cmtp2qvtb02bun701ypm3lgjc

@LottoLabs, 13 days ago · 50 likes · see the post

The point of https://localmaxxing.com is to let people like @fraserpricee get credit for their runs Why crop the photo 😂 if you want different aspect ratios I can ship that

@LottoLabs, 8 days ago · 43 likes · see the post

Much more to come Qwen 27b or die trying https://huggingface.co/Lottolabs/Qwen3.5-9B-TT-BFP4-P150

@LottoLabs, 13 days ago · 37 likes · see the post

Alternatives to LocalMaxxing

LocalMaxxing in numbers

FAQ

What is LocalMaxxing?

Qwen3.8-27B achieved 90.8 tok/s output speed on Radeon AI Pro R9700 · 32 GB ×3 using llama.cpp · Q8_0. See the full benchmark on LocalMaxxing. It was first shared on X 13 days ago and is ranked #374 on the AI Radar.

Is LocalMaxxing free?

Pricing is not stated on the page we read.

Who shared LocalMaxxing?

2 accounts on X, including @LottoLabs, @1337hero, in 4 posts totalling 22.9k views.

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. 27.2k posts from 4.8k X accounts over the last 14 days, 1.2k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:08 UTC. Full method.