Qwen3.8 27B
on M1 Max 32GB · MLX
Summary
User compares MLX and llama.cpp on Qwen3.8-27B. MLX reaches 15.81 t/s generation and 81.76 t/s prompt processing. llama.cpp reaches 9.69 t/s generation and 99.61 t/s prompt processing.
The llama.cpp run uses the UD-Q4_K_M quant.