DeepSeek V4.1 Flash 552B (16B active)
on M5 Max 128GB · ds4 · 2,048 ctx
Summary
User reports DeepSeek V4.1 Flash at ~30 tok/s decode at 2K context on an M5 Max 128GB, streaming a 341 GB Q2 GGUF from SSD.
Setup is a fork of antirez's ds4 engine (sf-ds4-1flash) with Metal backend, one machine, weights streamed from disk.
Decode is ~26 tok/s at 32K context and settles around 24 tok/s after an hour of heavy use. First token after an 8K prompt dropped from 1.23 s to 0.15 s. Prefill improved 45-99% and decode 62-78% versus upstream ds4. Output is bit-identical to ds4.