Dev Radar
Support
LiveUpdated 2026-09-19 18:06 UTC

amd users, rejoice. someone put an rx 7900 xt through the same a/b as everyone else, on…

amd users, rejoice. someone put an rx 7900 xt through the same a/b as everyone else, on omarchy, rocm 7.2, headless,…

This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev 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 Dev Radar as AI dev tools.

More dev work like this

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. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:06 UTC. Full method.