>>
Run gemma-4-31B on Lium
Google · Vision and text · 31.3B parameters · 62.5 GB BF16 weights · released 2026-03-12
It needs about 75 GB of VRAM. The cheapest setup that runs it is 2x RTX A6000 (96 GB), from $0.80 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/gemma-4-31B:
vllm serve google/gemma-4-31B --tensor-parallel-size 2Claude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does gemma-4-31B need?
About 62.5 GB for the released BF16 weights, so plan on 75 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 gemma-4-31B?
2x RTX A6000 (96 GB). On Lium that setup costs from $0.80 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt