amd users, rejoice. someone put an rx 7900 xt through the same a/b as everyone else, on…
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.
amd users, rejoice. someone put an rx 7900 xt through the same a/b as everyone else, on omarchy, rocm 7.2, headless, and the gaming card flies: 30.8 tok/s stock to 54.0 tok/s with one llama.cpp flag on, +75%, qwen 3.8 27b dense at 64k context on 20gb of vram with 2.5gb to spare. he swept it properly. draft depth 2, 3 and 4 land at 54.0, 54.7 and 53.1 tok/s, code climbs to 65.0 tok/s at depth 4 while prose falls to 34.9 tok/s, so depth 2 is the honest mixed load pick. the confidence gate costs 5% here, off. and it tracks the 7900 xtx row from the same file at exactly the bandwidth ratio betw
Posted by Sudo su (36.2k followers) 2 days ago · 44 likes · 4.1k views · view the original post on X. Kept by the AI Radar as Open & local models.
More AI work like this
- 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_
- your rtx 3060 was running bonsai 2 at 26 tok/s this morning and now does 40 tok/s, i… — @sudoingX
- Meet DeepSeek-V4.1-Flash: a blazing fast image-text-to-text model. It takes both images… — @HuggingModels
- Meet Edge0-35B-A3B-preview: a 35B parameter MoE model built for edge inference. It runs… — @HuggingModels
- Putting Jeff-1 out into the world, this is an attempt at a Jev like model, built on qwen… — @DJLougen
- Train a 9M parameter language model from scratch in five minutes. — @tom_doerr
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 18:45 UTC. Full method.