unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF
1k12.7m
1---2tags:3- unsloth4- qwen35- qwen6base_model:7- Qwen/Qwen3-Coder-30B-A3B-Instruct8library_name: transformers9license: apache-2.010license_link: https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE11pipeline_tag: text-generation12---13<div>14 <p style="margin-bottom: 0; margin-top: 0;">15 <strong>See <a href="https://huggingface.co/collections/unsloth/qwen3-680edabfb790c8c34a242f95">our collection</a> for all versions of Qwen3 including GGUF, 4-bit & 16-bit formats.</strong>16 </p>17 <p style="margin-bottom: 0;">18 <em>Learn to run Qwen3-Coder correctly - <a href="https://docs.unsloth.ai/basics/qwen3-coder">Read our Guide</a>.</em>19 </p>20<p style="margin-top: 0;margin-bottom: 0;">21 <em>See <a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0 GGUFs</a> for our quantization benchmarks.</em>22 </p>23 <div style="display: flex; gap: 5px; align-items: center; ">24 <a href="https://github.com/unslothai/unsloth/">25 <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">26 </a>27 <a href="https://discord.gg/unsloth">28 <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">29 </a>30 <a href="https://docs.unsloth.ai/basics/qwen3-coder">31 <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">32 </a>33 </div>34<h1 style="margin-top: 0rem;">✨ Read our Qwen3-Coder Guide <a href="https://docs.unsloth.ai/basics/qwen3-coder">here</a>!</h1>35</div>36 37- Fine-tune Qwen3 (14B) for free using our Google [Colab notebook](https://docs.unsloth.ai/get-started/unsloth-notebooks)!38- Read our Blog about Qwen3 support: [unsloth.ai/blog/qwen3](https://unsloth.ai/blog/qwen3)39- View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).40| Unsloth supports | Free Notebooks | Performance | Memory use |41|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|42| **Qwen3 (14B)** | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks) | 3x faster | 70% less |43| **GRPO with Qwen3 (8B)** | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks) | 3x faster | 80% less |44| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb) | 2.4x faster | 58% less |45| **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb) | 2x faster | 60% less |46| **Qwen2.5 (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb) | 2x faster | 60% less |47 48# Qwen3-Coder-30B-A3B-Instruct49<a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">50 <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>51</a>52 53## Highlights54 55**Qwen3-Coder** is available in multiple sizes. Today, we're excited to introduce **Qwen3-Coder-30B-A3B-Instruct**. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements: 56 57- **Significant Performance** among open models on **Agentic Coding**, **Agentic Browser-Use**, and other foundational coding tasks.58- **Long-context Capabilities** with native support for **256K** tokens, extendable up to **1M** tokens using Yarn, optimized for repository-scale understanding.59- **Agentic Coding** supporting for most platform such as **Qwen Code**, **CLINE**, featuring a specially designed function call format.60 6162 63## Model Overview64 65**Qwen3-Coder-30B-A3B-Instruct** has the following features:66- Type: Causal Language Models67- Training Stage: Pretraining & Post-training68- Number of Parameters: 30.5B in total and 3.3B activated69- Number of Layers: 4870- Number of Attention Heads (GQA): 32 for Q and 4 for KV71- Number of Experts: 12872- Number of Activated Experts: 873- Context Length: **262,144 natively**. 74 75**NOTE: 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.**76 77For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3-coder/), [GitHub](https://github.com/QwenLM/Qwen3-Coder), and [Documentation](https://qwen.readthedocs.io/en/latest/).78 79 80## Quickstart81 82We advise you to use the latest version of `transformers`.83 84With `transformers<4.51.0`, you will encounter the following error:85```86KeyError: 'qwen3_moe'87```88 89The following contains a code snippet illustrating how to use the model generate content based on given inputs. 90```python91from transformers import AutoModelForCausalLM, AutoTokenizer92 93model_name = "Qwen/Qwen3-Coder-30B-A3B-Instruct"94 95# load the tokenizer and the model96tokenizer = AutoTokenizer.from_pretrained(model_name)97model = AutoModelForCausalLM.from_pretrained(98 model_name,99 torch_dtype="auto",100 device_map="auto"101)102 103# prepare the model input104prompt = "Write a quick sort algorithm."105messages = [106 {"role": "user", "content": prompt}107]108text = tokenizer.apply_chat_template(109 messages,110 tokenize=False,111 add_generation_prompt=True,112)113model_inputs = tokenizer([text], return_tensors="pt").to(model.device)114 115# conduct text completion116generated_ids = model.generate(117 **model_inputs,118 max_new_tokens=65536119)120output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 121 122content = tokenizer.decode(output_ids, skip_special_tokens=True)123 124print("content:", content)125```126 127**Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value, such as `32,768`.**128 129For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.130 131## Agentic Coding132 133Qwen3-Coder excels in tool calling capabilities. 134 135You can simply define or use any tools as following example.136```python137# Your tool implementation138def square_the_number(num: float) -> dict:139 return num ** 2140 141# Define Tools142tools=[143 {144 "type":"function",145 "function":{146 "name": "square_the_number",147 "description": "output the square of the number.",148 "parameters": {149 "type": "object",150 "required": ["input_num"],151 "properties": {152 'input_num': {153 'type': 'number', 154 'description': 'input_num is a number that will be squared'155 }156 },157 }158 }159 }160]161 162import OpenAI163# Define LLM164client = OpenAI(165 # Use a custom endpoint compatible with OpenAI API166 base_url='http://localhost:8000/v1', # api_base167 api_key="EMPTY"168)169 170messages = [{'role': 'user', 'content': 'square the number 1024'}]171 172completion = client.chat.completions.create(173 messages=messages,174 model="Qwen3-Coder-30B-A3B-Instruct",175 max_tokens=65536,176 tools=tools,177)178 179print(completion.choice[0])180```181 182## Best Practices183 184To achieve optimal performance, we recommend the following settings:185 1861. **Sampling Parameters**:187 - We suggest using `temperature=0.7`, `top_p=0.8`, `top_k=20`, `repetition_penalty=1.05`.188 1892. **Adequate Output Length**: We recommend using an output length of 65,536 tokens for most queries, which is adequate for instruct models.190 191 192### Citation193 194If you find our work helpful, feel free to give us a cite.195 196```197@misc{qwen3technicalreport,198 title={Qwen3 Technical Report}, 199 author={Qwen Team},200 year={2025},201 eprint={2505.09388},202 archivePrefix={arXiv},203 primaryClass={cs.CL},204 url={https://arxiv.org/abs/2505.09388}, 205}206```207