Vision
How to deploy gemma-4-E4B-it on a GPU cloud
An 8.0B vision-language model that reads images alongside text. Full specs, license and use cases.
gemma-4-E4B-it size and hardware requirements
8.0B
Total parameters
Dense (no MoE)
Architecture
BF16
Published precision
17.9 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 14.9 GB | 17.9 GB | RTX A5000 | 1 | $0.160/hr |
| FP8 (quantized) | 7.4 GB | 8.9 GB | RTX 4070 Super | 1 | $0.110/hr |
| INT4 (quantized) | 3.7 GB | 4.5 GB | RTX 3060 | 1 | $0.080/hr |
How to run gemma-4-E4B-it
Run gemma-4-E4B-it with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve google/gemma-4-E4B-it --tensor-parallel-size 1Deploy gemma-4-E4B-it on Aquanode
Aquanode has no one-click deploy template for gemma-4-E4B-it; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× RTX A5000 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU pod