>>
Run paligemma-3b-pt-224 on Lium
Google · Vision and text · 2.9B parameters · 11.7 GB FP32 weights · released 2024-05-12
It needs about 15 GB of VRAM. The cheapest setup that runs it is RTX A4500 (20 GB), from $0.16 per hour, billed per second.
Other GPUs that run it
How to run it
Rent the pod above, open a terminal over SSH or Jupyter and serve google/paligemma-3b-pt-224:
vllm serve google/paligemma-3b-pt-224Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does paligemma-3b-pt-224 need?
About 11.7 GB for the released FP32 weights, so plan on 15 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 paligemma-3b-pt-224?
RTX A4500 (20 GB). On Lium that setup costs from $0.16 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt