Qwen 3 Coder

Qwen3 Coder is an instruction-tuned language model from Alibaba specialized in coding, flexibly switching from deep reasoning to fast response.

Use this snap to quickly install an optimized environment for local inference with Qwen3 Coder.

The snap includes the following hardware-optimized inference engines:

• cpu: Optimized for x64 and ARM (armv8, armv9) CPUs
• amd-gpu: ROCm-enabled GPU acceleration
• nvidia-gpu: CUDA-enabled GPU acceleration

The most suitable engine is automatically selected based on the available hardware.

Install:

sudo snap install qwen3-coder

Run:

qwen3-coder

Some accelerators require extra drivers to be usable with this snap: https://documentation.ubuntu.com/inference-snaps/how-to/setup/drivers/

License:

The Qwen3 Coder model is provided by Alibaba under the Apache License, Version 2.0: https://github.com/QwenLM/Qwen/blob/main/LICENSE

The licenses of all the bundled software can be found after installing the snap at /snap/qwen3-coder/current/usr/share/doc.