Run MiMo-V2.6-Flash-RL on Lium

Xiaomi · Text generation · 310.8B parameters · 172.9 GB 4-bit weights · released 2026-09-21

It needs about 208 GB of VRAM. The cheapest setup that runs it is 8x RTX 5090 (256 GB), from $4.00 per hour, billed per second.

Rent 8x RTX 5090

Other GPUs that run it

8x L40S	384 GB	from $4.24 / hour	Rent
8x Quadro RTX 8000	384 GB	reference $1.68 / hour	Request

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve XiaomiMiMo/MiMo-V2.6-Flash-RL:

vllm serve XiaomiMiMo/MiMo-V2.6-Flash-RL --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-V2.6-Flash-RL need?

About 172.9 GB for the released 4-bit weights, so plan on 208 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-V2.6-Flash-RL?

8x RTX 5090 (256 GB). On Lium that setup costs from $4.00 per hour, billed per second with no minimum.

All open models

For AI agents (CLI install, agent skill, headless signup): llms-full.txt