>>
Run gemma-3-12b-it-qat-q4_0-unquantized on Lium
Google · Vision and text · 12.2B parameters · 24.4 GB BF16 weights · released 2025-04-08
It needs about 30 GB of VRAM. The cheapest setup that runs it is RTX A6000 (48 GB), from $0.40 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-3-12b-it-qat-q4_0-unquantized:
vllm serve google/gemma-3-12b-it-qat-q4_0-unquantizedClaude Code and Codex can do all of it through the Lium CLI.
Frequently asked questions
How much VRAM does gemma-3-12b-it-qat-q4_0-unquantized need?
About 24.4 GB for the released BF16 weights, so plan on 30 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-3-12b-it-qat-q4_0-unquantized?
RTX A6000 (48 GB). On Lium that setup costs from $0.40 per hour, billed per second with no minimum.
For AI agents (CLI install, agent skill, headless signup): llms-full.txt