MiniMaxAI/MiniMax-M2 VRAM requirements

229B params, Grouped-query attention (GQA)

MiniMax-M2 needs about 230 GB of GPU memory for FP8 weights. The smallest fitting setup at 32k context is 2× NVIDIA B200. It supports 21 concurrent conversations with SGLang defaults.

GPU requirements by context length

8k context
GPUGPUsConcurrent users
NVIDIA B200264
NVIDIA H200 SXM25
NVIDIA H100 SXM450
NVIDIA H100 NVL464
NVIDIA A100 80GB SXM432
NVIDIA RTX PRO 6000 Blackwell Server Edition464
NVIDIA H20464
NVIDIA L40S864
32k context
GPUGPUsConcurrent users
NVIDIA B200221
NVIDIA H200 SXM21
NVIDIA H100 SXM412
NVIDIA H100 NVL424
NVIDIA A100 80GB SXM48
NVIDIA RTX PRO 6000 Blackwell Server Edition426
NVIDIA H20426
NVIDIA L40S819
128k context
GPUGPUsConcurrent users
NVIDIA B20025
NVIDIA H200 SXM414
NVIDIA H100 SXM43
NVIDIA H100 NVL46
NVIDIA A100 80GB SXM42
NVIDIA RTX PRO 6000 Blackwell Server Edition46
NVIDIA H2046
NVIDIA L40S84

FP8 weights, SGLang defaults, estimates.

Weights by precision

Weight memory
PrecisionWeightsSmallest fitting setup at 32k
FP8about 230 GB2x NVIDIA B200
INT4 (AWQ)about 127 GB1x NVIDIA B200

Model notes

Attention
Grouped-query attention (GQA)
Architecture
Mixture-of-Experts
Layers
62
Hidden size
3,072
Vocabulary
200,064

At 32k context, 28% of this card's usable memory is working as conversation cache.

Frequently asked questions

Will MiniMaxAI/MiniMax-M2 run on a single H100?
No, a single H100 SXM cannot hold MiniMaxAI/MiniMax-M2 at 32k context with FP8 weights. The model requires multiple GPUs.
What is the cheapest GPU setup for MiniMaxAI/MiniMax-M2?
The cheapest fitting setup at 32k context is 2x NVIDIA B200 with FP8 weights and SGLang defaults.
How much VRAM does MiniMaxAI/MiniMax-M2 need at 128k context?
At 128k context on the cheapest fitting setup, MiniMaxAI/MiniMax-M2 uses about 115 GB of VRAM per GPU for FP8 weights and about 8.3 GB per conversation for the KV cache. The total VRAM needed depends on the GPU count and parallelism configuration.
Can I run MiniMaxAI/MiniMax-M2 with INT4 quantization?
Yes, MiniMaxAI/MiniMax-M2 has INT4 weight figures. Its weights take about 127 GB in INT4 versus about 230 GB in FP8. INT4 can make the model fit on fewer GPUs, but check inference quality for your workload.

Want a different context length, GPU, or quantization? The calculator runs the same numbers live, preloaded with this model.

Open in calculator

Don't want to run this yourself? We deploy and operate it for you. Book a call →