DataLearner logo
QW

Qwen2.5-VL-72B-Instruct

Multimodal modelQwen2.5

Qwen2.5-VL-72B-Instruct

Release date: 2025-01-28Updated: 2025-02-20 19:34:281,304
Parameters
72B
Context length
128K
Chinese support
Supported
Reasoning ability

Qwen2.5-VL-72B-Instruct is an AI model published by Alibaba, released on 2025-01-28, for Multimodal model, with 72B parameters, and 128K context length, requiring about 144GB storage, with a 96.40 score on DocVQA.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Qwen2.5-VL-72B-Instruct

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
No data
Model type
Multimodal model
Modality (in / out)
No data
Release date
2025-01-28
Model file size
144GB
MoE architecture
No
Total params / Active params
72B / N/A
Knowledge cutoff
No data
Qwen2.5-VL-72B-Instruct

Open source & experience

Code license
Weights license
- Commercial use permitted
Live demo
No live demo
Qwen2.5-VL-72B-Instruct

Official resources

Paper
DataLearnerAI blog
No blog post yet
Qwen2.5-VL-72B-Instruct

API details

API speed
No data
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-¥0.0080/ 1K¥0.024/ 1K
Qwen2.5-VL-72B-Instruct

Benchmark Results

Qwen2.5-VL-72B-Instruct currently shows benchmark results led by DocVQA (1 / 5, score 96.40), MMMU (22 / 29, score 70.20). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

Multimodal Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
96.40
1 / 5
70.20
22 / 29

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Qwen2.5-VL-72B-Instruct

Publisher

Qwen2.5-VL-72B-Instruct

Model Overview

Qwen2.5-VL-72B-Instruct is an AI model published by Alibaba, released on 2025-01-28, for Multimodal model, with 72B parameters, and 128K context length, requiring about 144GB storage, with a 96.40 score on DocVQA.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code