Download
Qwen is a series of large language models developed by Alibaba Cloud, consisting of various pretrained versions like Qwen-1.8B, Qwen-7B, Qwen-14B, and Qwen-72B. These models, which range from smaller to larger configurations, are designed for a wide range of natural language processing tasks. They are openly available for research and commercial use, with Qwen's code and model weights shared on GitHub. Qwen's capabilities include text generation, comprehension, and conversation, making it a versatile tool for developers looking to integrate advanced AI functionalities into their applications.
Features
- Family of models of different sizes: Qwen-1.8B, 7B, 14B, 72B for both base and chat versions
- Quantization support: Int8, Int4 quantized versions to reduce memory/inference cost with little performance loss
- Long context support: large context windows (e.g. up to 32K tokens for some variants)
- Finetuning capabilities: full-parameter finetuning, LoRA, Q-LoRA, including distributed / multi-GPU setups
- Inference deployment via Transformers, ModelScope, Docker; also examples, demos, WebUI, CLI usage
- Strong benchmark performance across many tasks: multilingual understanding, math, code, reasoning, etc., often matching or exceeding other large models at similar sizes
Project Samples
License
Apache License V2.0Follow Qwen
Other Useful Business Software
Gemini 3 and 200+ AI Models on One Platform
Build generative AI apps with Vertex AI. Switch between models without switching platforms.
Rate This Project
Login To Rate This Project
User Reviews
-
Really great open source models
