LLM Inference Benchmark Explorer

Qwen3.8-27B on 1× DGX Spark — NVFP4, vLLM, TP1, speculative decoding inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelQwen3.8-27B
Parameters27B
Intelligence Index33.7
Agentic Index45.8
Device1× DGX Spark
QuantizationNVFP4
Max C1+
Chat Capacity4+
Agentic Capacity1+
TP—
DP—
PP—
EnginevLLM
Speculative DecodingYes
CTTFT (ms)TPS (tok/s)Status
128130.58PASS

In OpenZeka's measurement, Qwen3.8-27B (27B parameters), served in NVFP4 format with vLLM and speculative decoding on 1× DGX Spark, reached a generation speed of 30.6 tok/s per request and a time to first token (TTFT) of 281 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is at least 4 users for chat use and at least 1 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.

This configuration was measured with a single request only, so the estimate rests on one measurement.

Notes: eugr nightly. Single C=1 test (config matrix)

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