Qwen 3 is a large language model (LLM) developed by Alibaba. It is designed for various natural language processing tasks, including text generation, summarization, and question answering.
Use this snap to quickly install an optimized environment for local inference with Qwen 3.
The snap includes the following hardware-optimized inference engines:
- cpu: Optimized for x64 and ARM (armv8, armv9) CPUs
- nvidia-gpu: CUDA-enabled GPU acceleration
- amd-gpu: ROCm-enabled GPU acceleration for AMD GPUs
- mediatek-npu: Optimized for MediaTek Genio NPUs
The most suitable engine is automatically selected based on the available hardware.
Install:
sudo snap install qwen3
Run:
qwen3
Some accelerators require extra drivers to be usable with this snap:
https://documentation.ubuntu.com/inference-snaps/how-to/setup/drivers/
License:
The Qwen 3 model is provided by Alibaba under the Apache 2.0 license.
The licenses of all the bundled software can be found after installing the snap at
/snap/qwen3/current/usr/share/doc.