LLM Inference Benchmark Explorer

Gemma-4-31B-it on RTX PRO 6000 — NVFP4, vLLM, TP1 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelGemma-4-31B-it
Parameters31B
Intelligence Index14.7
Agentic Index4.2
DeviceRTX PRO 6000
QuantizationNVFP4
Max C32+
Chat Capacity53
Agentic Capacity18
TP—
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
13840.16PASS
24039.06PASS
47339.29PASS
837939.46PASS
168238.94PASS
3210837.22PASS

In this measurement, Gemma-4-31B-it (31B parameters), served in NVFP4 format with vLLM on RTX PRO 6000, reached a generation speed of 40.2 tok/s per request and a time to first token (TTFT) of 38 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 53 users for chat use and 18 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.