LLM Inference Benchmark Explorer

Qwen3.6-35B-A3B on 1× DGX Spark — FP8, vLLM, TP1, speculative decoding k=3 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelQwen3.6-35B-A3B
Parameters35B
Intelligence Index18.2
Agentic Index13.1
Device1× DGX Spark
QuantizationFP8
Max C16
Chat Capacity64
Agentic Capacity24
TP—
DP—
PP—
EnginevLLM
Speculative DecodingYes
CTTFT (ms)TPS (tok/s)Status
114064.78PASS
234749.22PASS
435430.57PASS
833028.13PASS
1646420.68PASS
3261214.82FAIL
6487810.28FAIL

In OpenZeka's measurement, Qwen3.6-35B-A3B (35B parameters), served in FP8 format with vLLM and speculative decoding on 1× DGX Spark, reached a generation speed of 64.8 tok/s per request and a time to first token (TTFT) of 140 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: Speculative MTP k=3. +24% TPS at C1 over FP8 without MTP

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