Qwen

Qwen is a family of large language and multimodal models developed by Alibaba Cloud.
It powers advanced AI capabilities for chat, content generation, and multimodal understanding.

Conversational AI text generation code generation translation summarization multimodal understanding image captioning question answering content creation

Tool Information

Primary Task	Chat
Category	communication-and-support
Sub Categories	chat-and-conversation generative-text copywriting text-to-code coding-assistants translation image-to-text
Pricing	Free and Paid (varies by deployment via Alibaba Cloud)
Website Status	🟢 Active

Qwen is the flagship AI model suite from Alibaba Cloud, designed to push the boundaries of large language and multimodal AI. It includes powerful LLMs for text-based reasoning and generation, as well as large multimodal models (LMMs) capable of interpreting and generating both text and images. Built with scalability, performance, and adaptability in mind, Qwen supports a wide range of use cases, from conversational agents and code generation to document analysis and creative tasks. By releasing models openly and iterating rapidly, Qwen aims to advance artificial general intelligence (AGI) research while enabling developers, researchers, and enterprises to build intelligent applications at scale.

Pros
Supports both language and multimodal tasks open model releases scalable for enterprise strong research backing multilingual capabilities

Cons
Some models require significant compute to run locally rapid updates may require frequent adaptation enterprise features tied to Alibaba Cloud ecosystem

AI Models

Qwen/CodeQwen1.5-7B Text Generation 7B

Qwen/CodeQwen1.5-7B-Chat Text Generation 7B

Qwen/CodeQwen1.5-7B-Chat-GGUF Text Generation 7B

Qwen/QVQ-72B-Preview Image-Text-to-Text 73B

Qwen/Qwen-1_8B-Chat Text Generation 2B

Qwen/Qwen-14B Text Generation 14B

Qwen/Qwen-14B-Chat Text Generation 14B

Qwen/Qwen-14B-Chat-Int4 Text Generation 3B

Qwen/Qwen-72B Text Generation 72B

Qwen/Qwen-72B-Chat Text Generation 72B

Qwen/Qwen-7B Text Generation 8B

Qwen/Qwen-7B-Chat Text Generation 8B

Qwen/Qwen-Audio Text Generation 8B

Qwen/Qwen-Audio-Chat Text Generation 8B

Qwen/Qwen-Image Text-to-Image

Qwen/Qwen-Image-Edit Image-to-Image

Qwen/Qwen-Image-Edit-2509 Image-to-Image

Qwen/Qwen-VL Text Generation

Qwen/Qwen-VL-Chat Text Generation

Qwen/Qwen-VL-Chat-Int4 Text Generation 4B

Qwen/Qwen1.5-0.5B Text Generation 0.6B

Qwen/Qwen1.5-0.5B-Chat Text Generation 0.6B

Qwen/Qwen1.5-1.8B-Chat Text Generation 2B

Qwen/Qwen1.5-110B Text Generation 111B

Qwen/Qwen1.5-110B-Chat Text Generation 111B

Qwen/Qwen1.5-110B-Chat-GPTQ-Int4 Text Generation 17B

Qwen/Qwen1.5-14B Text Generation 14B

Qwen/Qwen1.5-14B-Chat Text Generation 14B

Qwen/Qwen1.5-32B-Chat Text Generation 33B

Qwen/Qwen1.5-4B-Chat Text Generation 4B

Qwen/Qwen1.5-72B-Chat Text Generation 72B

Qwen/Qwen1.5-7B Text Generation 8B

Qwen/Qwen1.5-7B-Chat Text Generation 8B

Qwen/Qwen1.5-MoE-A2.7B Text Generation 14B

Qwen/Qwen1.5-MoE-A2.7B-Chat Text Generation 14B

Qwen/Qwen2-0.5B Text Generation 0.5B

Qwen/Qwen2-0.5B-Instruct Text Generation 0.5B

Qwen/Qwen2-1.5B Text Generation 2B

Qwen/Qwen2-1.5B-Instruct Text Generation 2B

Qwen/Qwen2-1.5B-Instruct-GGUF Text Generation 2B

Qwen/Qwen2-1.5B-Instruct-GPTQ-Int4 Text Generation 0.6B

Qwen/Qwen2-72B Text Generation 73B

Qwen/Qwen2-72B-Instruct Text Generation 73B

Qwen/Qwen2-72B-Instruct-GPTQ-Int4 Text Generation 12B

Qwen/Qwen2-7B Text Generation 8B

Qwen/Qwen2-7B-Instruct Text Generation 8B

Qwen/Qwen2-7B-Instruct-AWQ Text Generation 2B

Qwen/Qwen2-7B-Instruct-GGUF Text Generation 8B

Qwen/Qwen2-Audio-7B Audio-Text-to-Text 8B

Qwen/Qwen2-Audio-7B-Instruct Audio-Text-to-Text 8B

Qwen/Qwen2-Math-72B-Instruct Text Generation 73B

Qwen/Qwen2-VL-2B Image-Text-to-Text 2B

Qwen/Qwen2-VL-2B-Instruct Image-Text-to-Text 2B

Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4 Image-Text-to-Text 1B

Qwen/Qwen2-VL-72B-Instruct Image-Text-to-Text 73B

Qwen/Qwen2-VL-7B Image-Text-to-Text 8B

Qwen/Qwen2-VL-7B-Instruct Image-Text-to-Text 8B

Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4 Image-Text-to-Text 3B

Qwen/Qwen2.5-0.5B Text Generation 0.5B

Qwen/Qwen2.5-0.5B-Instruct Text Generation 0.5B

Qwen/Qwen2.5-0.5B-Instruct-GGUF Text Generation 0.6B

Qwen/Qwen2.5-1.5B Text Generation 2B

Qwen/Qwen2.5-1.5B-Instruct Text Generation 2B

Qwen/Qwen2.5-1.5B-Instruct-AWQ Text Generation 0.6B

Qwen/Qwen2.5-1.5B-Instruct-GGUF Text Generation 2B

Qwen/Qwen2.5-1.5B-Instruct-GPTQ-Int4 Text Generation 0.4B

Qwen/Qwen2.5-14B Text Generation 15B

Qwen/Qwen2.5-14B-Instruct Text Generation 15B

Qwen/Qwen2.5-14B-Instruct-1M Text Generation 15B

Qwen/Qwen2.5-14B-Instruct-AWQ Text Generation 3B

Qwen/Qwen2.5-32B Text Generation 33B

Qwen/Qwen2.5-32B-Instruct Text Generation 33B

Qwen/Qwen2.5-32B-Instruct-AWQ Text Generation 6B

Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4 Text Generation 6B

Qwen/Qwen2.5-32B-Instruct-GPTQ-Int8 Text Generation 10B

Qwen/Qwen2.5-3B Text Generation 3B

Qwen/Qwen2.5-3B-Instruct Text Generation 3B

Qwen/Qwen2.5-3B-Instruct-AWQ Text Generation 1.0B

Qwen/Qwen2.5-3B-Instruct-GGUF Text Generation 3B

Qwen/Qwen2.5-72B Text Generation 73B

Qwen/Qwen2.5-72B-Instruct Text Generation 73B

Qwen/Qwen2.5-72B-Instruct-AWQ Text Generation 12B

Qwen/Qwen2.5-72B-Instruct-GPTQ-Int4 Text Generation 12B

Qwen/Qwen2.5-7B Text Generation 8B

Qwen/Qwen2.5-7B-Instruct Text Generation 8B

Qwen/Qwen2.5-7B-Instruct-1M Text Generation 8B

Qwen/Qwen2.5-7B-Instruct-AWQ Text Generation 2B

Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4 Text Generation 2B

Qwen/Qwen2.5-Coder-1.5B Text Generation 2B

Qwen/Qwen2.5-Coder-1.5B-Instruct Text Generation 2B

Qwen/Qwen2.5-Coder-14B-Instruct Text Generation 15B

Qwen/Qwen2.5-Coder-14B-Instruct-AWQ Text Generation 3B

Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4 Text Generation 3B

Qwen/Qwen2.5-Coder-32B Text Generation 33B

Qwen/Qwen2.5-Coder-32B-Instruct Text Generation 33B

Qwen/Qwen2.5-Coder-32B-Instruct-AWQ Text Generation 6B

Qwen/Qwen2.5-Coder-32B-Instruct-GGUF Text Generation 33B

Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-Int4 Text Generation 6B

Qwen/Qwen2.5-Coder-3B-Instruct Text Generation 3B

Qwen/Qwen2.5-Coder-7B Text Generation 8B

Qwen/Qwen2.5-Coder-7B-Instruct Text Generation 8B

Qwen/Qwen2.5-Coder-7B-Instruct-AWQ Text Generation 2B

Qwen/Qwen2.5-Coder-7B-Instruct-GGUF Text Generation 8B

Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-Int4 Text Generation 2B

Qwen/Qwen2.5-Math-1.5B Text Generation 2B

Qwen/Qwen2.5-Math-1.5B-Instruct Text Generation 2B

Qwen/Qwen2.5-Math-7B Text Generation 8B

Qwen/Qwen2.5-Math-7B-Instruct Text Generation 8B

Qwen/Qwen2.5-Math-RM-72B Text Classification 73B

Qwen/Qwen2.5-Omni-3B Any-to-Any 6B

Qwen/Qwen2.5-Omni-7B Any-to-Any 11B

Qwen/Qwen2.5-VL-32B-Instruct Image-Text-to-Text 33B

Qwen/Qwen2.5-VL-32B-Instruct-AWQ Image-Text-to-Text 6B

Qwen/Qwen2.5-VL-3B-Instruct Image-Text-to-Text 4B

Qwen/Qwen2.5-VL-3B-Instruct-AWQ Image-Text-to-Text 1B

Qwen/Qwen2.5-VL-72B-Instruct Image-Text-to-Text 73B

Qwen/Qwen2.5-VL-72B-Instruct-AWQ Image-Text-to-Text 13B

Qwen/Qwen2.5-VL-7B-Instruct Image-Text-to-Text 8B

Qwen/Qwen2.5-VL-7B-Instruct-AWQ Image-Text-to-Text 3B

Qwen/Qwen3-0.6B Text Generation 0.8B

Qwen/Qwen3-0.6B-Base Text Generation 0.6B

Qwen/Qwen3-0.6B-FP8 Text Generation 0.8B

Qwen/Qwen3-1.7B Text Generation 2B

Qwen/Qwen3-1.7B-Base Text Generation 2B

Qwen/Qwen3-1.7B-GGUF Text Generation 2B

Qwen/Qwen3-14B Text Generation 15B

Qwen/Qwen3-14B-AWQ Text Generation 3B

Qwen/Qwen3-14B-Base Text Generation 15B

Qwen/Qwen3-235B-A22B Text Generation 235B

Qwen/Qwen3-235B-A22B-FP8 Text Generation 235B

Qwen/Qwen3-235B-A22B-GPTQ-Int4 Text Generation

Qwen/Qwen3-235B-A22B-Instruct-2507 Text Generation 235B

Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 Text Generation 235B

Qwen/Qwen3-235B-A22B-Thinking-2507 Text Generation 235B

Qwen/Qwen3-30B-A3B Text Generation 31B

Qwen/Qwen3-30B-A3B-Base Text Generation 31B

Qwen/Qwen3-30B-A3B-FP8 Text Generation 31B

Qwen/Qwen3-30B-A3B-GPTQ-Int4 Text Generation 5B

Qwen/Qwen3-30B-A3B-Instruct-2507 Text Generation 31B

Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 Text Generation 31B

Qwen/Qwen3-30B-A3B-Thinking-2507 Text Generation 31B

Qwen/Qwen3-30B-A3B-Thinking-2507-FP8 Text Generation 31B

Qwen/Qwen3-32B Text Generation 33B

Qwen/Qwen3-32B-AWQ Text Generation 6B

Qwen/Qwen3-32B-FP8 Text Generation 33B

Qwen/Qwen3-32B-GGUF Text Generation 33B

Qwen/Qwen3-4B Text Generation 4B

Qwen/Qwen3-4B-AWQ Text Generation 0.9B

Qwen/Qwen3-4B-Base Text Generation 4B

Qwen/Qwen3-4B-Instruct-2507 Text Generation 4B

Qwen/Qwen3-4B-Instruct-2507-FP8 Text Generation 4B

Qwen/Qwen3-4B-MLX-4bit Text Generation 0.6B

Qwen/Qwen3-4B-SafeRL Text Generation 4B

Qwen/Qwen3-4B-Thinking-2507 Text Generation 4B

Qwen/Qwen3-4B-Thinking-2507-FP8 Text Generation 4B

Qwen/Qwen3-8B Text Generation 8B

Qwen/Qwen3-8B-AWQ Text Generation 2B

Qwen/Qwen3-8B-Base Text Generation 8B

Qwen/Qwen3-8B-FP8 Text Generation 8B

Qwen/Qwen3-8B-GGUF Text Generation 8B

Qwen/Qwen3-Coder-30B-A3B-Instruct Text Generation 31B

Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 Text Generation 31B

Qwen/Qwen3-Coder-480B-A35B-Instruct Text Generation 480B

Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 Text Generation 480B

Qwen/Qwen3-Embedding-0.6B Feature Extraction 0.6B

Qwen/Qwen3-Embedding-0.6B-GGUF 0.6B

Qwen/Qwen3-Embedding-4B Feature Extraction 4B

Qwen/Qwen3-Embedding-8B Feature Extraction 8B

Qwen/Qwen3-Next-80B-A3B-Instruct Text Generation 81B

Qwen/Qwen3-Next-80B-A3B-Instruct-FP8 Text Generation

Qwen/Qwen3-Next-80B-A3B-Thinking Text Generation 81B

Qwen/Qwen3-Next-80B-A3B-Thinking-FP8 Text Generation

Qwen/Qwen3-Omni-30B-A3B-Captioner Any-to-Any 32B

Qwen/Qwen3-Omni-30B-A3B-Instruct Any-to-Any 35B

Qwen/Qwen3-Omni-30B-A3B-Thinking Any-to-Any 32B

Qwen/Qwen3-Reranker-0.6B Text Ranking 0.6B

Qwen/Qwen3-Reranker-4B Text Ranking 4B

Qwen/Qwen3-Reranker-8B Text Ranking 8B

Qwen/Qwen3-VL-235B-A22B-Instruct Image-Text-to-Text 236B

Qwen/Qwen3-VL-235B-A22B-Instruct-FP8 Image-Text-to-Text 236B

Qwen/Qwen3-VL-235B-A22B-Thinking Image-Text-to-Text 236B

Qwen/Qwen3-VL-235B-A22B-Thinking-FP8 Image-Text-to-Text 236B

Qwen/Qwen3-VL-2B-Instruct-FP8 Image-Text-to-Text 2B

Qwen/Qwen3-VL-2B-Thinking-FP8 Image-Text-to-Text 2B

Qwen/Qwen3-VL-30B-A3B-Instruct Image-Text-to-Text 31B

Qwen/Qwen3-VL-30B-A3B-Instruct-FP8 Image-Text-to-Text 31B

Qwen/Qwen3-VL-30B-A3B-Thinking Image-Text-to-Text 31B

Qwen/Qwen3-VL-30B-A3B-Thinking-FP8 Image-Text-to-Text 31B

Qwen/Qwen3-VL-32B-Instruct Image-Text-to-Text 33B

Qwen/Qwen3-VL-32B-Instruct-FP8 Image-Text-to-Text 33B

Qwen/Qwen3-VL-32B-Thinking-FP8 Image-Text-to-Text 33B

Qwen/Qwen3-VL-4B-Instruct Image-Text-to-Text 4B

Qwen/Qwen3-VL-4B-Instruct-FP8 Image-Text-to-Text 5B

Qwen/Qwen3-VL-4B-Thinking-FP8 Image-Text-to-Text 5B

Qwen/Qwen3-VL-8B-Instruct Image-Text-to-Text 9B

Qwen/Qwen3-VL-8B-Instruct-FP8 Image-Text-to-Text 9B

Qwen/Qwen3-VL-8B-Thinking Image-Text-to-Text 9B

Qwen/Qwen3-VL-8B-Thinking-FP8 Image-Text-to-Text 9B

Qwen/Qwen3Guard-Gen-0.6B Text Generation 0.8B

Qwen/Qwen3Guard-Gen-8B Text Generation 8B

Qwen/Qwen3Guard-Stream-8B Feature Extraction 8B

Qwen/QwQ-32B Text Generation 33B

Qwen/QwQ-32B-AWQ Text Generation 6B

Qwen/QwQ-32B-GGUF Text Generation 33B

Qwen/QwQ-32B-Preview Text Generation 33B

Frequently Asked Questions

1. What is Qwen?

Qwen is a family of large language and multimodal models developed by Alibaba Cloud. It's designed to push the boundaries of large language and multimodal AI, offering advanced capabilities for chat, content generation, and multimodal understanding.

2. What are the primary tasks Qwen can perform?

Qwen's primary task is chat, but it also excels at conversational AI, text generation, code generation, translation, summarization, multimodal understanding, image captioning, question answering, and content creation.

3. What types of tasks is Qwen suited for?

Qwen supports a wide range of use cases, including conversational agents, code generation, document analysis, and creative tasks. Its capabilities extend to both text-based and multimodal applications.

4. Who is Qwen designed for?

Qwen is designed for developers, researchers, and enterprises who need to build intelligent applications at scale. Its open model releases aim to benefit a broad range of users.

5. What are the advantages of using Qwen?

Qwen offers several advantages, including support for both language and multimodal tasks, open model releases for accessibility, scalability for enterprise use, strong research backing, and multilingual capabilities.

6. What are some limitations of Qwen?

Some Qwen models may require significant computing resources to run locally. Also, frequent updates may necessitate adaptation, and some enterprise features are tied to the Alibaba Cloud ecosystem.

7. What category does Qwen belong to?

Qwen falls under the business-operations category.