>>
Run MiMo-V2.5-Pro on Lium
Xiaomi · Text generation · 1T parameters · 1033.4 GB FP8 weights · released 2026-04-27
It needs about 1241 GB of VRAM. The cheapest setup that runs it is 8x B200 (1440 GB), reference $44.80 per hour, billed per second.
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve XiaomiMiMo/MiMo-V2.5-Pro:
vllm serve XiaomiMiMo/MiMo-V2.5-Pro --tensor-parallel-size 8Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does MiMo-V2.5-Pro need?
About 1033.4 GB for the released FP8 weights, so plan on 1241 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 MiMo-V2.5-Pro?
8x B200 (1440 GB). On Lium that setup costs reference $44.80 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt