LLM Inference Benchmark Explorer

Gemma-4-31B-it on DGX B300 — BF16, vLLM, TP1 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelGemma-4-31B-it
Parameters31B
Intelligence Index19
Agentic Index4.2
DeviceDGX B300
QuantizationBF16
Max C64+
Chat Capacity168
Agentic Capacity59
TP—
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
13574.85PASS
24172.14PASS
44870.62PASS
85770.63PASS
168368.65PASS
328163.73PASS
649255.63PASS

In OpenZeka's measurement, Gemma-4-31B-it (31B parameters), served in BF16 format with vLLM on DGX B300, reached a generation speed of 74.8 tok/s per request and a time to first token (TTFT) of 35 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 168 users for chat use and 59 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.