LLM Inference Benchmark Explorer

DeepSeek-V4.1-Flash on DGX B300 — FP8, vLLM, TP4, speculative decoding k=3 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelDeepSeek-V4.1-Flash
Parameters763B
Intelligence Index39.5
Agentic Index—
DeviceDGX B300
QuantizationFP8
Max C64+
Chat Capacity256+
Agentic Capacity96+
TP4
DP—
PP—
EnginevLLM
Speculative DecodingYes
CTTFT (ms)TPS (tok/s)Status
164290.70PASS
264331.13PASS
473284.09PASS
880232.56PASS
16142193.42PASS
32167166.11PASS
64123117.51PASS

In this measurement, DeepSeek-V4.1-Flash (763B parameters), served in FP8 format with vLLM and speculative decoding on DGX B300 (TP=4), reached a generation speed of 290.7 tok/s per request and a time to first token (TTFT) of 64 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is at least 256 users for chat use and at least 96 for agentic use. The realistic capacity will likely fall between these two values. In scenarios dominated by coding, tool use, long workflows and multi-agent use, capacity approaches the agentic estimate; where shorter interactions, standard conversations and lighter tasks dominate, it approaches the chat estimate.

“At least” means the configuration met the speed targets even at the highest load tested, so the real capacity may be higher.

Notes: DSpark k=3, 1M context. Model: deepseek-ai/DeepSeek-V4.1-Flash

Intelligence Index and Agentic Index values are published by Artificial Analysis and are reproduced here with attribution.