LLM Inference Benchmark Explorer

Qwen3.6-27B on 1× DGX Spark — NVFP4, vLLM, TP1, speculative decoding inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelQwen3.6-27B
Parameters27B
Intelligence Index21.4
Agentic Index18.5
Device1× DGX Spark
QuantizationNVFP4
Max C4
Chat Capacity16
Agentic Capacity6
TP—
DP—
PP—
EnginevLLM
Speculative DecodingYes
CTTFT (ms)TPS (tok/s)Status
151922.56PASS
263523.85PASS
485022.33PASS
859219.75FAIL
1683915.78FAIL

In this measurement, Qwen3.6-27B (27B parameters), served in NVFP4 format with vLLM and speculative decoding on 1× DGX Spark, reached a generation speed of 22.6 tok/s per request and a time to first token (TTFT) of 519 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 16 users for chat use and 6 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.