Y
Hacker News
new
|
ask
|
show
|
jobs
by
instagib
111 days ago
1 4090, Qwen3.5-35B-A3B-UD-MXFP4_MOE, 64k context, 122 t/s. Llama.cpp
1 comments
mirekrusin
111 days ago
I believe it's mentioned that MXFP4 performs surprisingly bad, you may want to try other Q4s.
link