Run OLMo-2-0325-32B-Instruct on Lium

Ai2 · Text generation · 32.2B parameters · 64.5 GB BF16 weights · released 2025-03-12

It needs about 78 GB of VRAM. The cheapest setup that runs it is 2x RTX A6000 (96 GB), from $0.80 per hour, billed per second.

Rent 2x RTX A6000

Other GPUs that run it

A100 80GB PCIe	80 GB	from $0.81 / hour	Rent
4x RTX 3090	96 GB	from $1.16 / hour	Rent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve allenai/OLMo-2-0325-32B-Instruct:

vllm serve allenai/OLMo-2-0325-32B-Instruct --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-2-0325-32B-Instruct 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-2-0325-32B-Instruct?

2x RTX A6000 (96 GB). On Lium that setup costs from $0.80 per hour, billed per second with no minimum.

All open models

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