# dev.to: Running Gemma 4 on EC2 G5g: Graviton2 AMD with NVIDIA GPU — retained record

> Retained dev-ecosystems record from dev-ecosystems:devto.

Canonical: https://highsignal.app/data/records/316c931d29face69

[← sources](https://highsignal.app/data)


source: [dev-ecosystems](https://highsignal.app/data/dev-ecosystems) (dev-ecosystems:devto)  published 2026-08-13 18:42 ingested 2026-08-14 07:29

[original source ↗](https://dev.to/gde/running-gemma-4-on-ec2-g5g-graviton2-amd-with-nvidia-gpu-25ci)

## retained text



```
A field report on serving Gemma 4 E2B under vLLM on AWS G5g — the only aarch64 + SM 7.5 hardware there is. No published build covers that combination, AWS quietly solves half of it, and the thing that actually blocks you is 64 KiB of shared memory.

tags: aws, vllm, cuda, machinelearning

reactions=7 | comments=0
```



document fetched 2026-08-19 06:44
