>>

Run MiMo-V2-Flash on Lium

Xiaomi · Text generation · 309.8B parameters · 313.1 GB FP8 weights · released 2025-12-16
It needs about 376 GB of VRAM. The cheapest setup that runs it is 8x L40S (384 GB), from $4.24 per hour, billed per second.
Rent 8x L40S

Other GPUs that run it

4x RTX 6000D384 GBfrom $5.20 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve XiaomiMiMo/MiMo-V2-Flash:
vllm serve XiaomiMiMo/MiMo-V2-Flash --tensor-parallel-size 8
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does MiMo-V2-Flash need?

About 313.1 GB for the released FP8 weights, so plan on 376 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-Flash?

8x L40S (384 GB). On Lium that setup costs from $4.24 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt