Qwen 3.5

Qwen 3.5 is a multimodal instruction-tuned model from Qwen with vision capabilities, optimized directly for your hardware. It runs efficiently on pure CPU or leverages CUDA-enabled NVIDIA GPU acceleration.

Use this snap to quickly install an optimized environment for local inference with Qwen 3.5.

The snap includes the following hardware-optimized inference engines:

• cpu: Optimized for x64 and ARM (armv8, armv9) CPUs
• nvidia-gpu: CUDA-enabled GPU acceleration
• nvidia-jetson-orin: CUDA-enabled GPU acceleration for NVIDIA Jetson Orin devices

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

Install:

sudo snap install qwen3-5

Run:

qwen3-5

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

License:

The Qwen 3.5 model is provided by Alibaba (Qwen) under the Apache 2.0 license.

The licenses of all the bundled software can be found after installing the snap at /snap/qwen3-5/current/usr/share/doc.