QwenLM / Qwen3-Coder

💜 Qwen Chat &nbsp&nbsp | &nbsp&nbsp🤗 Hugging Face &nbsp&nbsp | &nbsp&nbsp🤖 ModelScope &nbsp&nbsp | &nbsp&nbsp 📑 Blog &nbsp&nbsp ｜ &nbsp&nbsp📖 Documentation 🌍 WebDev &nbsp&nbsp | &nbsp&nbsp💬 WeChat (微信) &nbsp&nbsp | &nbsp&nbsp🫨 Discord &nbsp&nbsp | &nbsp&nbsp 📄 Arxiv &nbsp&nbsp | &nbsp&nbsp 👽 Qwen Code Visit our Hugging Face or ModelScope organization (click links above), search checkpoints with names starting with , and you will find all you need! Enjoy! --- Table of Contents • Introduction • Key Features • Basic Information • Quick Start • 👉🏻 Chat with Qwen3-Coder • Fill in the middle with Qwen3-Coder • Use Cases • Example: Releasing a Website • Example: Desktop Tidy • Example: Zombies vs. Plants • Example: Sound ASCII Art • Example: Vibe Checking • Example: Parkour Game • Star History • Citation • Contact Us --- Qwen3-Coder-Next: Pushing Small Hybrid Models on Agentic Coding Introduction We are announcing Qwen3-Coder, our most agentic code model to date. **Qwen3-Coder** is available in multiple sizes, **Qwen3-Coder-480B-A35B-Instruct**, **Qwen3-Coder-30B-A3B-Instruct**, **Qwen3-Coder-Next**, offering exceptional performance in both coding and agentic tasks. **Qwen3-Coder-Next**, an open-weight language model designed specifically for coding agents and local development. Built on top of **Qwen3-Next-80B-A3B-Base**, which adopts a novel architecture with hybrid attention and MoE, Qwen3-Coder-Next has been agentically trained at scale on large-scale executable task synthesis, environment interaction, and reinforcement learning, obtaining strong coding and agentic capabilities with significantly lower inference costs. Key Features 💻 **Efficiency-Performance Tradeoff**: among open models on **Agentic Coding**, **Agentic Browser-Use**, and other foundational coding tasks, achieving results comparable to Claude Sonnet. 🛠 **Scaling Agentic Coding**: supporting most platforms such as **Qwen Code**, **CLINE**, **Claude Code**, featuring a specially designed function call format; 📚 **Long-context Capabilities**: with native support for **256K** tokens, extendable up to **1M** tokens using Yarn, optimized for repository-scale understanding. --- Basic Information • ✨ Supporting long context understanding and generation with the context length of 256K tokens; • ✨ Supporting 358 coding languages; Click to view all supported languages • ✨ Retain strengths in math and general capabilities from base model. > [!Important] > > Qwen3-Coder function calling relies on our new tool parser in both **SGLang** and **vLLM** here . > > We updated both the special tokens and their corresponding token ids, in order to maintain consistency with Qwen3. Please make sure to use the new tokenizer. | model name | type | length | Download | |-----------------------------|----------|--------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Qwen3-Coder-Next | instruct | 256k | 🤗 Hugging Face • 🤖 ModelScope | | Qwen3-Coder-Next-Base | base | 256k | 🤗 Hugging Face • 🤖 ModelScope | | Qwen3-Coder-480B-A35B-Instruct | instruct | 256k | 🤗 Hugging Face • 🤖 ModelScope | | Qwen3-Coder-30B-A3B-Instruct | instruct | 256k | 🤗 Hugging Face • 🤖 ModelScope | | Qwen3-Coder-Next-FP8 | instruct | 256k | 🤗 Hugging Face • 🤖 ModelScope | Qwen3-Coder-Next-GGUF | instruct | 256k | 🤗 Hugging Face • 🤖 ModelScope | | Qwen3-Coder-480B-A35B-Instruct-FP8 | instruct | 256k | 🤗 Hugging Face • 🤖 ModelScope | | Qwen3-Coder-30B-A3B-Instruct-FP8 | instruct | 256k | 🤗 Hugging Face • 🤖 ModelScope | Detailed performance and introduction are shown in this 📑 blog . --- Quick Start > [!Important] > **Qwen3-Coder** are instruct models for chatting; > > This model supports only non-thinking mode and does not generate blocks in its output. Meanwhile, specifying is no longer required. > 👉🏻 Chat with Qwen3-Coder You can write several lines of code with to chat with Qwen3-Coder-Next. Essentially, we build the tokenizer and the model with the method, and we use the generate method to perform chatting with the help of the chat template provided by the tokenizer. Below is an example of how to chat with **Qwen3-Coder-Next**: The function is used to convert the messages into a format that the model can understand. The argument is used to add a generation prompt, which refers to to the input. Notably, we apply the ChatML template for chat models following our previous practice. The argument is used to set the maximum length of the response. The function is used to decode the response. In terms of the input, the above messages are an example to show how to format your dialog history and system prompt. You can use the other sizes of instruct models in the same way. Fill in the middle with Qwen3-Coder The code insertion task, also referred to as the "fill-in-the-middle" challenge, requires the insertion of code segments in a manner that bridges the gaps within a given code context. For an approach aligned with best practices, we recommend adhering to the formatting guidelines outlined in the paper "Efficient Training of Language Models to Fill in the Middle" [arxiv]. > [!Important] > It should be noted that FIM is supported in every version of Qwen3-Coder. Qwen3-Coder-Next is shown here as an example. > The prompt should be structured as follows: Following the approach mentioned, an example would be structured in this manner: Use Cases Example: Releasing a Website Prompt with OpenClaw Example: Desktop Tidy Prompt with Qwen Code Example: Zombies vs. Plants Prompt with Claude Code Example: Sound ASCII Art Prompt with Cline Example: Vibe Checking Prompt with Browser Use Agent Example: Parkour Game Prompt with Qwen Chat Web Dev --- Star History --- Citation If you find our work helpful, feel free to give us a cite. `bibtex @techreport{qwen_qwen3_coder_next_tech_repor…