Vision
How to deploy gemma-4-26B-A4B-it on a GPU cloud
A 25.8B vision-language model that reads images alongside text. Full specs, license and use cases.
gemma-4-26B-A4B-it size and hardware requirements
25.8B
Total parameters
Dense (no MoE)
Architecture
BF16
Published precision
57.7 GB
Min VRAM (native)
| Precision | Weight size on disk | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 48.1 GB | 57.7 GB | A100 | 1 | $1.00/hr |
| FP8 (quantized) | 24.0 GB | 28.8 GB | RTX 4080 Super | 1 | $0.395/hr |
| INT4 (quantized) | 12.0 GB | 14.4 GB | RTX 6000 | 1 | $0.158/hr |
How to run gemma-4-26B-A4B-it
Run gemma-4-26B-A4B-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-4-26B-A4B-it --tensor-parallel-size 1Deploy gemma-4-26B-A4B-it on Aquanode
Aquanode has no one-click deploy template for gemma-4-26B-A4B-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× A100 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