DeepSeek V4 Flash 284B (13B active)
on NVIDIA RTX 5090 · llama.cpp · 1,000,000 ctx
Sep 7, 2026
Use cases
long-context
Summary
User reports DeepSeek V4 Flash at 1M context on an RTX 5090, with prefill at 159 t/s and decode at 13.7 t/s.
Setup is a patched llama.cpp, with peak VRAM around 31 GiB.
The user verified the run with a needle-in-haystack test.