>>

Run Olmo-3-32B-Think on Lium

Ai2 · Text generation · 32.2B parameters · 64.5 GB BF16 weights · released 2025-11-19
It needs about 78 GB of VRAM. The cheapest setup that runs it is 2x RTX A6000 (96 GB), from $0.84 per hour, billed per second.

Other GPUs that run it

4x RTX 309096 GBfrom $0.88 / hourRent
H100 PCIe80 GBfrom $1.75 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve allenai/Olmo-3-32B-Think:
vllm serve allenai/Olmo-3-32B-Think --tensor-parallel-size 2
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does Olmo-3-32B-Think need?

About 64.5 GB for the released BF16 weights, so plan on 78 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 Olmo-3-32B-Think?

2x RTX A6000 (96 GB). On Lium that setup costs from $0.84 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt