What it takes to serve it
GPU memory to run it for inference, with the smallest GPU setup that holds it and the lowest price on Arrakis right now.
| Precision | Memory and the smallest setup |
|---|---|
| 16-bit | 75 GB: one H100 or A100, H100 from $1.65 per GPU-hour |
| 8-bit | 38 GB: one L40S, RTX 6000 Ada or RTX A6000, L40S from $0.44 per GPU-hour |
| 4-bit | 19 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour |
What it takes to fine-tune it
QLoRA trains adapters on a 4-bit frozen model, LoRA on a 16-bit one, and full fine-tuning updates every weight. Figures are before activations, which grow with batch size and sequence length.
| Method | Memory and the smallest setup |
|---|---|
| QLoRA | 22 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour |
| LoRA | 75 GB: one H100 or A100, H100 from $1.65 per GPU-hour |
| Full fine-tuning | 500 GB: 2 × B300, from $9.20 per hour for all 2 |
About the model
From its card and files on Hugging Face. Memory figures here follow the GPU memory guide.
- Parameters
- 31B
- Context window (tokens)
- 262,144
- Published in
- BF16
- License
- apache-2.0
- Released
- 2026-03-11
- Weights
- google/gemma-4-31B-it
Deploy it on Arrakis
Open Models in the console, choose vLLM, SGLang or llama.cpp, and rent a GPU it fits on. You get an OpenAI-compatible endpoint with its own API key, and root SSH to the machine. Or run it yourself on any machine with enough GPU memory:
vLLM
vllm serve google/gemma-4-31B-it --tensor-parallel-size 1Questions
Live prices for every GPU are on the GPU prices page.
How much GPU memory does gemma-4-31B-it need?
To serve it, about 75 GB in 16-bit, 38 GB in 8-bit, 19 GB in 4-bit, including about 20% for the KV cache and activations. To fine-tune it, about 22 GB with QLoRA, 75 GB with LoRA and 500 GB for full fine-tuning with Adam, before activations.
Can I run gemma-4-31B-it on one GPU?
Yes. In 16-bit it needs about 75 GB, which fits on one H100 or A100.
What does it cost to run gemma-4-31B-it?
In 16-bit it needs one H100 or A100; in 4-bit, one RTX 4090 or RTX 3090. Each setup on this page shows the lowest price per GPU-hour on Arrakis right now, and you pay by the hour from a prepaid balance.
How do I deploy gemma-4-31B-it on Arrakis?
Open Models in the Arrakis console, paste google/gemma-4-31B-it, choose vLLM, SGLang or llama.cpp, and rent a GPU it fits on. You get an OpenAI-compatible endpoint with its own API key, and root SSH to the machine.