deepseek-v4.1IMAGE

DeepSeek V4.1 Flash in Project Maya: 2,000 tps prefill, 50 tps decode at 256k

Project Maya added DeepSeek V4.1 Flash and measured 2,000 tps prefill and 50 tps decode at 256k context, slightly slower than GLM-5.3-Flash on the same hardware, with room for optimization.

Axitek

@axitekArchived 11 days agoOriginally posted 2026.10.20

DeepSeek V4.1 Flash in Project Maya: 2,000 tps prefill, 50 tps decode at 256k

Axitek @axitekOriginally posted 2026.10.20

Open original on X

Deepseek-v4.1-Flash is now available in Project Maya - and it’s fast right out of the gate! Testing at 256k context: 🔥Prefill: 2,000 tps 🚀Decode: 50 tps A little bit slower compared to GLM-5.3-Flash on the same hardware, I bet there’s still optimization headroom.

x.com/axitek/status/2112316819885477966Archived 2026.10.20 12:04