QwenReleased on Feb 28, 2025

Qwen2.5 VL 32B Instruct: Benchmarks, Pricing & Context Window

Qwen2.5 VL 32B Instruct is a language model from Qwen, released in February 2025, with multimodal input.

Qwen2.5-VL is a vision-language model from the Qwen family. Key enhancements include visual understanding (objects, text, charts, layouts), visual agent capabilities (tool use, computer/phone control), long video comprehension with event

Qwen2.5 VL 32B Instruct API

API access coming soon

Qwen2.5 VL 32B Instruct will be available through our gateway shortly.

Qwen2.5 VL 32B Instruct examples

Recent arena outputs from Qwen2.5 VL 32B Instruct, picked from the highest-ranked matchups.

Qwen2.5 VL 32B Instruct license

Qwen2.5 VL 32B Instruct is released under the Apache 2.0 license, which permits commercial use, has 33.5B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
33.5B

Apache License 2.0 - allows commercial use

FAQ

Common questions about Qwen2.5 VL 32B Instruct.

When was Qwen2.5 VL 32B Instruct released?

Qwen2.5 VL 32B Instruct was released on February 28, 2025 by Qwen. This is the official Qwen2.5 VL 32B Instruct release date tracked on LLM Stats.

How many parameters does Qwen2.5 VL 32B Instruct have?

Qwen2.5 VL 32B Instruct has 33.5 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Qwen2.5 VL 32B Instruct?

Qwen2.5 VL 32B Instruct was created by Qwen.

What is the license for Qwen2.5 VL 32B Instruct?

Qwen2.5 VL 32B Instruct is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Is Qwen2.5 VL 32B Instruct multimodal?

Yes, Qwen2.5 VL 32B Instruct is multimodal and can accept both text and images as input.

Where is the Qwen2.5 VL 32B Instruct paper or technical report?

Qwen2.5 VL 32B Instruct has a paper or technical report available at https://arxiv.org/pdf/2502.13923. Use that source for architecture, training, release and evaluation details.