>>

Run medgemma-4b-it on Lium

Google · Vision and text · 4.3B parameters · 8.6 GB BF16 weights · released 2025-05-19
It needs about 11 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
L40S48 GBfrom $0.38 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve google/medgemma-4b-it:
vllm serve google/medgemma-4b-it
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does medgemma-4b-it need?

About 8.6 GB for the released BF16 weights, so plan on 11 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 medgemma-4b-it?

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