All model and GPU pairings
MiniMax M3 428BNVIDIA Blackwell

Running MiniMax M3 on GB300 NVL72

Quick answer

MiniMax M3 runs on GB300 NVL72: 39 benchmarked configs so far. See the interactivity ladder below for measured operating points.

Benchmarked configs

39

Serving engines

Dynamo vLLM

Precisions

fp4, fp8

Run dates

2026-06-262026-08-21

Throughput at every interactivity target

Serving is a trade-off: push more concurrent users through a GPU and each user's tokens arrive slower. The ladder below reads the measured frontier at each per-user speed target on the AgentX agentic coding workload, using the best engine and precision at that point.

Per-user targetTokens/s per GPU$ / 1M tokensEnginePrecision
30 tok/s--Dynamo vLLMfp4
50 tok/s--Dynamo vLLMfp4
75 tok/s--Dynamo vLLMfp4
100 tok/s31,391$0.020Dynamo vLLMfp4
150 tok/s25,555$0.025Dynamo vLLMfp4
200 tok/s16,334$0.039Dynamo vLLMfp4

Frequently asked questions

How fast is MiniMax M3 on GB300 NVL72?
The InferenceX fleet has 39 benchmarked configs for this pairing; see the interactivity ladder above for the operating points reached so far.
How much does it cost to serve MiniMax M3 on GB300 NVL72?
Cost per million tokens is derived from measured throughput and $/GPU/hr rates from the SemiAnalysis AI Cloud TCO model; it appears once this pairing reaches the primary interactivity tier.
Which serving engines run MiniMax M3 on GB300 NVL72?
The runs behind this page used Dynamo vLLM in FP4, FP8, including disaggregated prefill and multi-node serving. Engines are rebuilt and re-benchmarked continuously, so the best config can change between visits.
How are these MiniMax M3 numbers measured?
Every number is measured on real GB300 NVL72 hardware by the InferenceX fleet, sweeping concurrency on the AgentX agentic coding workload to trace the throughput-versus-interactivity frontier; the newest run landed on 2026-08-21. The same derivation powers the InferenceX overview leaderboard.

Explore the data