>>

Run WeMM-Video-9B on Lium

Tencent · Vision and text · 10.5B parameters · 21 GB BF16 weights · released 2026-11-17
It needs about 26 GB of VRAM. The cheapest setup that runs it is 2x RTX A4000 (32 GB), from $0.24 per hour, billed per second.

Other GPUs that run it

RTX 4080 SUPER 32GB32 GBfrom $0.30 / hourRent
L4048 GBfrom $0.33 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve tencent/WeMM-Video-9B:
vllm serve tencent/WeMM-Video-9B --tensor-parallel-size 2
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does WeMM-Video-9B need?

About 21 GB for the released BF16 weights, so plan on 26 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 WeMM-Video-9B?

2x RTX A4000 (32 GB). On Lium that setup costs from $0.24 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt