Visit our Hugging Face or ModelScope organization (click links above), search checkpoints with names starting with Qwen3-Coder-, and you will find all you need! Enjoy!
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;
✨ 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 <a href="https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/">here</a>.
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.
Detailed performance and introduction are shown in this <a href="https://qwenlm.github.io/blog/qwen3-coder-next/">📑 blog</a>.
Quick Start
[!Important]
Qwen3-Coder are instruct models for chatting;
This model supports only non-thinking mode and does not generate <think></think> blocks in its output. Meanwhile, specifying enable_thinking=False is no longer required.
👉🏻 Chat with Qwen3-Coder
You can write several lines of code with transformers to chat with Qwen3-Coder-Next. Essentially, we build the tokenizer and the model with the from_pretrained 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 apply_chat_template() function is used to convert the messages into a format that the model can understand.
The add_generation_prompt argument is used to add a generation prompt, which refers to <|im_start|>assistant\n to the input. Notably, we apply the ChatML template for chat models following our previous practice.
The max_new_tokens argument is used to set the maximum length of the response. The tokenizer.batch_decode() 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.
Following the approach mentioned, an example would be structured in this manner:
from transformers import AutoTokenizer, AutoModelForCausalLM
# load model
device = "cuda" # the device to load the model onto
TOKENIZER = AutoTokenizer.from_pretrained("Qwen/Qwen3-Coder-Next")
MODEL = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Coder-Next", device_map="auto").eval()
input_text = """<|fim_prefix|>def quicksort(arr):
if len(arr) <= 1:
return arr
pivot = arr[len(arr) // 2]
<|fim_suffix|>
middle = [x for x in arr if x == pivot]
right = [x for x in arr if x > pivot]
return quicksort(left) + middle + quicksort(right)<|fim_middle|>"""
messages = [
{"role": "system", "content": "You are a code completion assistant."},
{"role": "user", "content": input_text}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = TOKENIZER([text], return_tensors="pt").to(model.device)
# Use `max_new_tokens` to control the maximum output length.
eos_token_ids = [151659, 151661, 151662, 151663, 151664, 151643, 151645]
generated_ids = MODEL.generate(model_inputs.input_ids, max_new_tokens=512, do_sample=False, eos_token_id=eos_token_ids)[0]
# The generated_ids include prompt_ids, we only need to decode the tokens after prompt_ids.
output_text = TOKENIZER.decode(generated_ids[len(model_inputs.input_ids[0]):], skip_special_tokens=True)
print(f"Prompt: {input_text}\n\nGenerated text: {output_text}")
Use Cases
Example: Releasing a Website
next week we will release new coder model, can you collect the history of qwen coder and write a web page, the release the website with the nginx, you can seach how to do this in alibaba cloud linux first
Build an interactive ASCII art drawing tool with sound feedback. The application should:
1. Create a canvas where users can draw by clicking and dragging
2. Place different ASCII characters or symbols when the user draws
3. Play corresponding musical notes when each character is placed
4. Include multiple pattern sets with different characters and
corresponding note scales
5. Add a pattern switcher button to cycle through different
character/sound themes
6. Include a clear button to reset the canvas
7. Support both mouse and touch input for mobile compatibility
The application should be creative and fun to use, creating an audio-visual experience where patterns of characters create both visual art and musical patterns. Ensure the musical notes are harmonious when played in sequence.
Example: Vibe Checking
Vibe test this website. Click around, try things, report what's broken.
Example: Parkour Game
Create an interactive real-time particle system using HTML5 Canvas:
Core Features:
- Render 800-1200 animated particles with physics-based movement
- Mouse cursor exerts attractive/repulsive force on nearby particles
- Click to toggle between attraction and repulsion modes
- Particles respond with smooth acceleration and velocity calculations
Technical Requirements:
- Use requestAnimationFrame for optimal performance
- Implement force calculation based on distance from cursor
- Add visual feedback: particle glow, color variation, and fade effects
- Include performance monitoring (FPS counter)
Deliverables:
- Single HTML file with embedded CSS and JavaScript
- Clean, commented code following best practices
- Responsive design compatible with modern browsers
Star History
Citation
If you find our work helpful, feel free to give us a cite.
@article{Qwen3-Coder-Next,
title={Qwen3-Coder-Next Technical Report},
author={Ruisheng Cao and Mouxiang Chen and Jiawei Chen and Zeyu Cui and Yunlong Feng and Binyuan Hui and Yuheng Jing and Kaixin Li and Mingze Li and Junyang Lin and Zeyao Ma and Kashun Shum and Xuwu Wang and Jinxi Wei and Jiaxi Yang and Jiajun Zhang and Lei Zhang and Zongmeng Zhang and Wenting Zhao and Fan Zhou},
journal={arXiv preprint arXiv:2603.00729},
year={2026},
}
Contact Us
If you are interested to leave a message to either our research team or product team, join our Discord or WeChat groups!
Ecosystem Role
Standard MoltPulse indexed agent.
Embed Badge
Show off your Pulse Score in your GitHub README to build trust and rank higher.
