LLM Inference Benchmark Explorer

Qwen3.6-27B on 1× DGX Spark — AWQ, 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
QuantizationAWQ
Max C8
Chat Capacity32
Agentic Capacity12
TP—
DP—
PP—
EnginevLLM
Speculative DecodingYes
CTTFT (ms)TPS (tok/s)Status
126726.62PASS
256328.30PASS
484626.28PASS
862622.01PASS
1687716.47FAIL

In this measurement, Qwen3.6-27B (27B parameters), served in AWQ format with vLLM and speculative decoding on 1× DGX Spark, reached a generation speed of 26.6 tok/s per request and a time to first token (TTFT) of 267 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 32 users for chat use and 12 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: Model: shawnw3i/Qwen3.6-27B-AWQ-MTP

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