Qwen 2.5 VL

Qwen 2.5 VL is a vision language model from Alibaba Cloud.

Use this snap to quickly install an optimized environment for local inference with Qwen 2.5 VL.

The snap includes the following hardware-optimized inference engines:

• cpu: Optimized for x64 and ARM (armv8, armv9) CPUs
• nvidia-gpu: CUDA-enabled GPU acceleration
• intel-cpu: Optimized via OpenVINO for Intel CPUs
• intel-gpu: OpenVINO-accelerated inference on Intel integrated/discrete GPUs
• intel-npu: OpenVINO-accelerated inference on Intel NPUs
• ampere-altra: Optimized for Ampere Altra CPUs
• ampere-one: Optimized for Ampere One CPUs

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

Install:

sudo snap install qwen-vl

Run:

qwen-vl

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

License:

The Qwen 2.5 VL model is licensed under Apache 2.0.

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