> ## Documentation Index > Fetch the complete documentation index at: https://mintlify.com/QwenLM/Qwen/llms.txt > Use this file to discover all available pages before exploring further. # Introduction > Qwen is a series of large language models from Alibaba Cloud, featuring models from 1.8B to 72B parameters with state-of-the-art performance # Welcome to Qwen Qwen (通义千问) is a series of open-source large language models developed by Alibaba Cloud. The models range from 1.8B to 72B parameters and include both pretrained base models and chat-aligned variants optimized for conversational AI. Get started with Qwen in minutes Choose the right model for your use case Customize models for your domain Explore the complete API ## Key Features Choose from 1.8B, 7B, 14B, and 72B parameter models to balance performance and efficiency Run models efficiently with GPTQ Int4/Int8 and KV cache quantization Process up to 32K tokens in a single context window Enable tool use and agent capabilities with built-in function calling Strong performance on both Chinese and English tasks Deploy with OpenAI-compatible API endpoints ## Model Variants Qwen offers two main types of models: **Qwen-1.8B**, **Qwen-7B**, **Qwen-14B**, **Qwen-72B** Pretrained language models trained on over 2.2-3.0 trillion tokens. Ideal for: * Further fine-tuning on domain-specific data * Research and experimentation * Building custom chat applications **Qwen-1.8B-Chat**, **Qwen-7B-Chat**, **Qwen-14B-Chat**, **Qwen-72B-Chat** Fine-tuned models aligned with human preferences through supervised fine-tuning. Ideal for: * Conversational AI applications * Question answering systems * Task-oriented dialogue * Function calling and tool use ## Performance Highlights Qwen-72B achieves state-of-the-art performance among open-source models: * **MMLU**: 77.4% (outperforms LLaMA2-70B and GPT-3.5) * **C-Eval**: 83.3% (leading performance on Chinese benchmarks) * **GSM8K**: 78.9% (strong mathematical reasoning) * **HumanEval**: 35.4% (competitive coding capabilities) For detailed benchmark results and methodology, see the [Benchmarks](/resources/benchmarks) page and [Technical Report](/resources/technical-report). ## Getting Started Install the required packages: ```bash theme={null} pip install transformers>=4.32.0 torch>=2.0.0 ``` Load and use a Qwen model in just a few lines: ```python theme={null} from transformers import AutoModelForCausalLM, AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval() response, history = model.chat(tokenizer, "Hello!", history=None) print(response) ``` Discover quantization, fine-tuning, and deployment options in the documentation ## Next Steps Set up your environment and install Qwen Compare model sizes and capabilities Optimize memory and speed with quantization Deploy Qwen in production environments ## Community and Support View source code and contribute Find answers to common questions **Note**: This repository (QwenLM/Qwen) focuses on the first generation of Qwen models. For Qwen2, please visit [QwenLM/Qwen2](https://github.com/QwenLM/Qwen2).