LLM Inference Benchmark Explorer

MiniMax-M2.7 on 2× DGX Spark — NVFP4, vLLM, TP2 inference benchmark

Open this configuration in the LLM Inference Benchmark Explorer

ModelMiniMax-M2.7
Parameters229B
Intelligence Index22.8
Agentic Index15.3
Device2× DGX Spark
QuantizationNVFP4
Max C2
Chat Capacity8
Agentic Capacity3
TP2
DP—
PP—
EnginevLLM
Speculative Decoding—
CTTFT (ms)TPS (tok/s)Status
128926.64PASS
225824.40PASS
440917.98FAIL
847512.98FAIL

In OpenZeka's measurement, MiniMax-M2.7 (229B parameters), served in NVFP4 format with vLLM on 2× DGX Spark (TP=2), reached a generation speed of 26.6 tok/s per request and a time to first token (TTFT) of 289 ms with a single request.

Considering the speed targets and the available KV cache capacity, the estimated capacity is 8 users for chat use and 3 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.

Notes: Best 2-node config. 55% faster than PP=2.

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