LLM Inference Benchmark Explorer

Qwen3-235B-A22B on DGX B300 — BF16, vLLM, TP4 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelQwen3-235B-A22B
Parameters235B
Intelligence Index9.5
Agentic Index—
DeviceDGX B300
QuantizationBF16
Max C32+
Chat Capacity128+
Agentic Capacity48+
TP4
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
113283.92PASS
224171.18PASS
426764.87PASS
827856.93PASS
1626749.55PASS
3233231.41PASS

In OpenZeka's measurement, Qwen3-235B-A22B (235B parameters), served in BF16 format with vLLM on DGX B300 (TP=4), reached a generation speed of 83.9 tok/s per request and a time to first token (TTFT) of 132 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is at least 128 users for chat use and at least 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.

“At least” means the configuration met the speed targets even at the highest load tested, so the real capacity may be higher.

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