Download
Qwen3 is a cutting-edge large language model (LLM) series developed by the Qwen team at Alibaba Cloud. The latest updated version, Qwen3-235B-A22B-Instruct-2507, features significant improvements in instruction-following, reasoning, knowledge coverage, and long-context understanding up to 256K tokens. It delivers higher quality and more helpful text generation across multiple languages and domains, including mathematics, coding, science, and tool usage. Various quantized versions, tools/pipelines provided for inference using quantized formats (e.g. GGUF, etc.). Coverage for many languages in training and usage, alignment with human preferences in open-ended tasks, etc.
Features
- Multiple model sizes including 0.6B, 1.7B, 4B, 8B, 14B, 30B-A3B, 32B, 235B-A22B (dense & MoE)
- Dual modes: “Thinking” mode (deep reasoning) and “Instruct” / non-thinking mode (more efficient, general usage)
- Very long context / token windows (256K tokens, extendable to ~1M tokens) for handling large documents, long interactions etc.
- Quantization support: various quantized versions, tools / pipelines provided for inference using quantized formats (e.g. GGUF etc.)
- Multilingual capabilities: coverage for many languages in training and usage, alignment with human preferences in open-ended tasks etc.
- Broad deployment support: works with Transformers, llama.cpp, SGLang, vLLM, Ollama etc.; support for different platforms (servers, local inference), demonstration code, technical reports
Project Samples
Follow Qwen3
Other Useful Business Software
Try Google Cloud Risk-Free With $300 in Credit
Use your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
Rate This Project
Login To Rate This Project
User Reviews
-
Best open source AI model!
