DeepSeek V4 Flash 284B (13B active)
on NVIDIA RTX 5090 · vLLM · 1,048,576 ctx
Sep 7, 2026
Summary
User reports full 1M context on a single RTX 5090 with CPU/RAM offloading, at about 800 t/s prefill and over 15 t/s decode.
Setup uses DSpark speculative decoding with dynamic acceptance rates, with two routed MoE layers kept GPU-resident.