LLM Inference Benchmark Explorer

MiniMax-M2.7 on 4× DGX Spark — NVFP4, vLLM, TP4 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelMiniMax-M2.7
Parameters229B
Intelligence Index22.8
Agentic Index15.3
Device4× DGX Spark
QuantizationNVFP4
Max C4
Chat Capacity16
Agentic Capacity6
TP4
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
123531.32PASS
227827.95PASS
435922.82PASS
844016.84FAIL
1642213.14FAIL
325139.53FAIL
646306.98FAIL

In this measurement, MiniMax-M2.7 (229B parameters), served in NVFP4 format with vLLM on 4× DGX Spark (TP=4), reached a generation speed of 31.3 tok/s per request and a time to first token (TTFT) of 235 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 16 users for chat use and 6 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.