LLM Inference Benchmark Explorer

DeepSeek V4 Flash 0731 on 8× DGX Spark — NVFP4, vLLM, TP2, DP4 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelDeepSeek V4 Flash 0731
Parameters304B
Intelligence Index34.3
Agentic Index41
Device8× DGX Spark
QuantizationNVFP4
Max C16
Chat Capacity64
Agentic Capacity24
TP2
DP4
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
128948.86PASS
232643.12PASS
434638.47PASS
841129.85PASS
1652323.37PASS
3265316.44FAIL
6493910.71FAIL

In OpenZeka's measurement, DeepSeek V4 Flash 0731 (304B parameters), served in NVFP4 format with vLLM on 8× DGX Spark (TP=2, DP=4), reached a generation speed of 48.9 tok/s per request and a time to first token (TTFT) of 289 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 64 users for chat use and 24 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.

Notes: TP=2, DP=4. Best for high concurrency.

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