>>

Run granite-switch-4.1-30b on Lium

IBM · Text generation · 30B parameters · 60 GB BF16 weights · released 2026-10-14
It needs about 72 GB of VRAM. The cheapest setup that runs it is 2x L40 (96 GB), from $0.66 per hour, billed per second.

Other GPUs that run it

4x RTX 309096 GBfrom $0.80 / hourRent
2x RTX A600096 GBfrom $0.84 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve ibm-granite/granite-switch-4.1-30b:
vllm serve ibm-granite/granite-switch-4.1-30b --tensor-parallel-size 2
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does granite-switch-4.1-30b need?

About 60 GB for the released BF16 weights, so plan on 72 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-switch-4.1-30b?

2x L40 (96 GB). On Lium that setup costs from $0.66 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt