Qwen3.8 125B (6B active) Flash-Next
on M3 Max
Summary
User reports running Qwen3.8 Flash-Next at 40 t/s on an M3 Max.
User says prefill feels stagnant and tried approximating the KV cache with QFN, getting about 2x prefill (400 t/s to ~850 t/s) but needle test accuracy suffered.
User asks whether anyone is working on improving prefill speed or if it is a hardware limitation.