>>

Run Molmo2-O-7B on Lium

Ai2 · Vision and text · 7.8B parameters · 31 GB FP32 weights · released 2025-12-14
It needs about 38 GB of VRAM. The cheapest setup that runs it is RTX A6000 (48 GB), from $0.42 per hour, billed per second.

Other GPUs that run it

2x RTX 309048 GBfrom $0.44 / hourRent
H100 80GB HBM380 GBfrom $2.00 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve allenai/Molmo2-O-7B:
vllm serve allenai/Molmo2-O-7B
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does Molmo2-O-7B need?

About 31 GB for the released FP32 weights, so plan on 38 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 Molmo2-O-7B?

RTX A6000 (48 GB). On Lium that setup costs from $0.42 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt