Linked List
login
sign up
julianmb/q38rocm: Qwen 3.8 27B ROCmFP4 on AMD Strix Halo (Ryzen AI Max+ 395). Up to 36 tok/s via MTP Speculation, TurboQuant & Mesa RADV Wave64.
github.com
saved by
0 people
related read on
prabanta-dev/janas: 37 tok/s from Qwen3-Next-80B (48 GB) ...
from the discussion
Feed
Explore
Sign In