Qwen3.8 125B (6B active) Flash-Next
on 2× NVIDIA RTX 3090 · llama.cpp · 261,888 ctx
Use cases
coding
Summary
User reports decode improving from 25-29 to 37-41 t/s with the UD-Q4_K_XL quant, expert cache, and MTP.
Prefill runs 180-195 t/s, load time is 2 min, and cache hit rate is 90-92%.
MTP acceptance is 50-58% on reasoning and 94% on code emission. Host RAM is 73 GB pinned plus 28 GB PLE. The branch is available.