Latest Content
MiniMax M2.7 icon

MiniMax M2.7

NVIDIA
MiniMax M2.7 is a large-scale Mixture-of-Experts (MoE) language model developed by MiniMax for coding, agentic workflows, and enterprise automation tasks. It features a 229B parameter architecture with ~10B active parameters, built on a 62-layer transformer with 48 attention heads and a 3,072 hidden size. It employs a 256-expert MoE architecture with 8 experts per token and supports up to a 200K context window. It is optimized for autonomous agent teams, iterative self-improvement, and complex real-world task execution.
TypeMoE LLM
CapabilitiesText Generation, Instruction Following, Reasoning, Mathematical Reasoning+5 more
Release Date18 March, 2026
Links
Blog|HF Model Card
LicenseModified MIT

Inference Instructions

Deploy and run this model on NVIDIA B200 GPUs using the command below. Copy the command to get started with inference.

CONSOLE
docker run -it --rm 
 --runtime=nvidia 
 --gpus all 
 --ipc=host 
 --shm-size=128g 
 -p 8000:8000 
 -e VLLM_FLOAT32_MATMUL_PRECISION=high 
 -v ~/.cache/huggingface:/root/.cache/huggingface 
 -e HF_TOKEN='YOUR_HF_TOKEN' 
 vllm/vllm-openai:v0.18.1 
 MiniMaxAI/MiniMax-M2.7 
  --tensor-parallel-size 8 
 --enable-expert-parallel 
 --max-model-len auto 
  --max-num-batched-tokens 65536 
  --gpu-memory-utilization 0.95 
  --tool-call-parser minimax_m2 
 --reasoning-parser minimax_m2_append_think 
 --enable-auto-tool-choice 
 --max-num-seqs 1024 
  --trust-remote-code

Model Benchmarks

Each model was tested with a fixed input size and total token volume while increasing concurrency to measure serving performance under load.

ITL vs Concurrency

Time to First Token

Throughput Scaling

Total Tokens/sec vs Avg TTFT

Vultr Cloud GPU

NVIDIA HGX B200

Deploy NVIDIA B200 on Vultr Cloud GPU

Deploy NVIDIA B200 instancesContact Sales