LLM Inference Benchmark Explorer

Qwen3-4B-Instruct-2507 on 1× DGX Spark — NVFP4, vLLM, TP1 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelQwen3-4B-Instruct-2507
Parameters4B
Intelligence Index8.8
Agentic Index—
Device1× DGX Spark
QuantizationNVFP4
Max C32+
Chat Capacity78
Agentic Capacity19
TP—
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
14249.63PASS
24450.42PASS
46048.71PASS
87746.66PASS
169144.07PASS
3211439.30PASS

In OpenZeka's measurement, Qwen3-4B-Instruct-2507 (4B parameters), served in NVFP4 format with vLLM on 1× DGX Spark, reached a generation speed of 49.6 tok/s per request and a time to first token (TTFT) of 42 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 78 users for chat use and 19 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.

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