LLM Inference Benchmark Explorer

MiniMax-M2.5 on DGX B300 — FP8, vLLM, TP2 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelMiniMax-M2.5
Parameters229B
Intelligence Index22.8
Agentic Index—
DeviceDGX B300
QuantizationFP8
Max C32+
Chat Capacity126
Agentic Capacity31
TP2
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
116972.78PASS
219457.90PASS
425156.47PASS
829748.88PASS
1642040.44PASS
3234031.92PASS

In this measurement, MiniMax-M2.5 (229B parameters), served in FP8 format with vLLM on DGX B300 (TP=2), reached a generation speed of 72.8 tok/s per request and a time to first token (TTFT) of 169 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 126 users for chat use and 31 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.