LLM Inference Benchmark Explorer

Qwen3.6-35B-A3B on 4× DGX Spark — NVFP4, vLLM, TP4 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelQwen3.6-35B-A3B
Parameters35B
Intelligence Index18.2
Agentic Index13.1
Device4× DGX Spark
QuantizationNVFP4
Max C32
Chat Capacity128
Agentic Capacity48
TP4
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
123191.16PASS
228373.49PASS
427764.80PASS
853151.88PASS
1659540.24PASS
3269129.67PASS
64483315.03FAIL

In OpenZeka's measurement, Qwen3.6-35B-A3B (35B parameters), served in NVFP4 format with vLLM on 4× DGX Spark (TP=4), reached a generation speed of 91.2 tok/s per request and a time to first token (TTFT) of 231 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 128 users for chat use and 48 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: nvidia/Qwen3.6-35B-A3B-NVFP4

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