DeepSeek-V4.1-Flash

Deepseek family · 552.0B params

Evidence: 39 sourced runs · 1 independent source · first recorded Sep 10, 2026 · last recorded Oct 15, 2026. What these labels mean.

What the DeepSeek-V4.1-Flash numbers mean

The fastest verified result on our board is 231.6 output tok/s on an RTX PRO 6000 Blackwell x4 at FP4+FP8 native with a 65536-token context. That is about 4.3 ms per generated token — 500 tokens takes roughly 2.2 seconds. Prompt processing on the same record runs at 7346.3 tok/s, so a 2,000-token prompt is read in about 0.3 seconds. Across the 39 records we hold for this model the range is 2.7–231.6 tok/s on 6 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does DeepSeek-V4.1-Flash need?

DeepSeek-V4.1-Flash has 552.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Models with a similar footprint

Ranked by distance from DeepSeek-V4.1-Flash's parameter count. Full benchmark board.

All benchmarks Methodology