Qwen3.8 125B (6B active) Flash-Next
on M1 Ultra 128GB · llama.cpp
Sep 7, 2026
Summary
User benchmarks a custom llama.cpp branch with faster Metal inference and n-gram SSD offload at pp512 530.18 t/s and tg128 31.17 t/s with resident n-gram.
The model is 68.37 GiB and 125.74 B params.
With SSD read mode, pp512 is 197.92 t/s and tg128 is 28.47 t/s.