QwenReleased on Aug 29, 2024

Qwen2-VL-72B-Instruct: Benchmarks, Pricing & Context Window

Qwen2-VL-72B-Instruct is a language model from Qwen, released in August 2024, with multimodal input.

An instruction-tuned, large multimodal model that excels at visual understanding and step-by-step reasoning. It supports image and video input, with dynamic resolution handling and improved positional embeddings (M-ROPE), enabling advanced

Qwen2-VL-72B-Instruct API

API access coming soon

Qwen2-VL-72B-Instruct will be available through our gateway shortly.

Qwen2-VL-72B-Instruct examples

Recent arena outputs from Qwen2-VL-72B-Instruct, picked from the highest-ranked matchups.

Qwen2-VL-72B-Instruct license

Qwen2-VL-72B-Instruct is released under the tongyi-qianwen license, which restricts commercial use, has 73.4B parameters, has a knowledge cutoff of June 2023.

License
tongyi-qianwen
Non-commercial
Parameters
73.4B
Knowledge cutoff
June 2023

FAQ

Common questions about Qwen2-VL-72B-Instruct.

What is the Qwen2-VL-72B-Instruct release date?

Qwen2-VL-72B-Instruct was released on August 29, 2024 by Qwen.

Who created Qwen2-VL-72B-Instruct?

Qwen2-VL-72B-Instruct was created by Qwen.

How many parameters does Qwen2-VL-72B-Instruct have?

Qwen2-VL-72B-Instruct has 73.4 billion parameters.

What is the license for Qwen2-VL-72B-Instruct?

Qwen2-VL-72B-Instruct is released under the tongyi-qianwen license.

What is the knowledge cutoff date for Qwen2-VL-72B-Instruct?

Qwen2-VL-72B-Instruct has a knowledge cutoff of June 2023. This means the model was trained on data up to this date and may not have information about events after this time.

Is Qwen2-VL-72B-Instruct multimodal?

Yes, Qwen2-VL-72B-Instruct is a multimodal model that can process both text and images as input.