Local AI with Gemma 3 inference snap
Gemma 3 is a multimodal language model from Google DeepMind.
Use this snap to quickly install an optimized environment for local inference with Gemma 3.
The snap includes the following hardware-optimized inference engines:
- cpu: Optimized for various CPUs
- nvidia-gpu: CUDA-optimized for NVIDIA GPUs
- amd-gpu: ROCm-optimized for AMD GPUs
- intel-cpu: Optimized for Intel CPUs using OpenVINO Model Server
- intel-gpu: Optimized for Intel GPUs using OpenVINO Model Server
The most suitable engine is automatically selected based on the available hardware.
Install:
sudo snap install gemma3
Run:
gemma3
Some accelerators require extra drivers to be usable with this snap:
https://documentation.ubuntu.com/inference-snaps/how-to/setup/drivers/
License:
The use of Gemma 3 is subject to Google's Gemma Terms of Use:
https://ai.google.dev/gemma/terms
The licenses of all the bundled software can be found after installing the snap at
/snap/gemma3/current/usr/share/doc.