DeepSeek V4.1 Flash hits 314 tok/s decode on four 2019 GPUs

A user runs unmodified V4.1 Flash weights on four 2019-era GPUs, hitting 314 tok/s peak decode on real coding work and ~200 tok/s average in coding agents.

Qubitium

@qubitiumArchived 7 days agoOriginally posted 2026.10.24

Qubitium @qubitiumOriginally posted 2026.10.24

Open original on X

DeepSeek v4.1 Flash 1017 just reached batch 1 peak decode of 314 t/s on real coding work, not simulation. Avg 200 t/s on my coding agents. Setup is 4x 2019 era gpu. Full native, unmodified weights. Imagine what I can do with 2025 gpus. 😎

x.com/qubitium/status/2113817933424312680Archived 2026.10.24 12:05

Open original on X