Qwen3.8 27B
on RTX 6000 · llama.cpp
Summary
User reports dflash2 speeds up Qwen 3.8 27B up to 4x, with a median of 140.6 tok/s against a baseline of 47.4 tok/s.
Gains vary by task and are sometimes only 1.5x.
The user is from the atomic.chat team.
on RTX 6000 · llama.cpp