>>

Run granite-3.3-2b-instruct on Lium

IBM · Text generation · 2.5B parameters · 5.1 GB BF16 weights · released 2025-04-09
It needs about 7 GB of VRAM. The cheapest setup that runs it is RTX 5060 Ti (16 GB), from $0.12 per hour, billed per second.

Other GPUs that run it

RTX A450020 GBfrom $0.17 / hourRent
CMP 170HX8 GBfrom $0.37 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve ibm-granite/granite-3.3-2b-instruct:
vllm serve ibm-granite/granite-3.3-2b-instruct
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does granite-3.3-2b-instruct need?

About 5.1 GB for the released BF16 weights, so plan on 7 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 granite-3.3-2b-instruct?

RTX 5060 Ti (16 GB). On Lium that setup costs from $0.12 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt