>>
Run MiniMax-M3 on Lium
MiniMax · Vision and text · 427B parameters · 854.2 GB BF16 weights · released 2026-06-02
It needs about 1026 GB of VRAM. The cheapest setup that runs it is 8x H200 (1128 GB), from $30.00 per hour, billed per second.
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve MiniMaxAI/MiniMax-M3:
vllm serve MiniMaxAI/MiniMax-M3 --tensor-parallel-size 8Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does MiniMax-M3 need?
About 854.2 GB for the released BF16 weights, so plan on 1026 GB with room for activations and KV cache at a short context. Longer contexts and bigger batches need more.
What GPU should I rent to run MiniMax-M3?
8x H200 (1128 GB). On Lium that setup costs from $30.00 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt