DeepSeek V4 Flash 284B (13B active)
on M2 Ultra 192GB · llama.cpp · 1,000,000 ctx
Sep 7, 2026
Summary
User reports DeepSeek V4 Flash at 25.8 t/s, with a 42 t/s peak, on an M2 Ultra with 60 cores and 192gb.
Setup is a custom llama.cpp fork with the model repacked losslessly to 141GiB, smaller than the public GGUFs, no KV cache quant, and an SSD KV cache with dynamic lanes, 1M context total across 8 lanes.
Prompt processing is about 250 t/s at 8k-32k. The user compares this with 16 t/s on an M3 Ultra.