🚀 Qwen3-235B-A22B
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. This is a powerful large language model in the Qwen series, offering advanced reasoning and multilingual support.
✨ Features
Qwen3 Highlights
Qwen3 is the latest generation of large language models in the Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
- Unique Mode Switching: It supports seamless switching between thinking mode (for complex logical reasoning, math, and coding) and non-thinking mode (for efficient, general-purpose dialogue) within a single model, ensuring optimal performance across various scenarios.
- Enhanced Reasoning: There is a significant enhancement in its reasoning capabilities, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
- Superior Alignment: It has superior human preference alignment, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
- Agent Capabilities: It shows expertise in agent capabilities, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
- Multilingual Support: It supports 100+ languages and dialects with strong capabilities for multilingual instruction following and translation.
Model Overview
Property |
Details |
Model Type |
Causal Language Models |
Training Stage |
Pretraining & Post-training |
Number of Parameters |
235B in total and 22B activated |
Number of Parameters (Non-Embedding) |
234B |
Number of Layers |
94 |
Number of Attention Heads (GQA) |
64 for Q and 4 for KV |
Number of Experts |
128 |
Number of Activated Experts |
8 |
Context Length |
32,768 natively and 131,072 tokens with YaRN |
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.
📦 Installation
The code of Qwen3-MoE has been in the latest Hugging Face transformers
and we advise you to use the latest version of transformers
.
With transformers<4.51.0
, you will encounter the following error:
KeyError: 'qwen3_moe'
💻 Usage Examples
Basic Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen3-235B-A22B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
try:
index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
index = 0
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
print("thinking content:", thinking_content)
print("content:", content)
Advanced Usage
Deployment
For deployment, you can use sglang>=0.4.6.post1
or vllm>=0.8.5
or to create an OpenAI-compatible API endpoint:
For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
Switching Between Thinking and Non-Thinking Mode
⚠️ Important Note
The enable_thinking
switch is also available in APIs created by SGLang and vLLM.
Please refer to our documentation for SGLang and vLLM users.
enable_thinking=True
By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting enable_thinking=True
or leaving it as the default value in tokenizer.apply_chat_template
, the model will engage its thinking mode.
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True
)
In this mode, the model will generate think content wrapped in a <think>...</think>
block, followed by the final response.
⚠️ Important Note
For thinking mode, use Temperature=0.6
, TopP=0.95
, TopK=20
, and MinP=0
(the default setting in generation_config.json
). DO NOT use greedy decoding, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the Best Practices section.
enable_thinking=False
We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=False
)
In this mode, the model will not generate any think content and will not include a <think>...</think>
block.
⚠️ Important Note
For non-thinking mode, we suggest using Temperature=0.7
, TopP=0.8
, TopK=20
, and MinP=0
. For more detailed guidance, please refer to the Best Practices section.
Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input
We provide a soft switch mechanism that allows users to dynamically control the model's behavior when enable_thinking=True
. Specifically, you can add /think
and /no_think
to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.
Here is an example of a multi-turn conversation:
from transformers import AutoModelForCausalLM, AutoTokenizer
class QwenChatbot:
def __init__(self, model_name="Qwen/Qwen3-235B-A22B"):
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
self.model = AutoModelForCausalLM.from_pretrained(model_name)
self.history = []
def generate_response(self, user_input):
messages = self.history + [{"role": "user", "content": user_input}]
text = self.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
inputs = self.tokenizer(text, return_tensors="pt")
response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
response = self.tokenizer.decode(response_ids, skip_special_tokens=True)
self.history.append({"role": "user", "content": user_input})
self.history.append({"role": "assistant", "content": response})
return response
if __name__ == "__main__":
chatbot = QwenChatbot()
user_input_1 = "How many r's in strawberries?"
print(f"User: {user_input_1}")
response_1 = chatbot.generate_response(user_input_1)
print(f"Bot: {response_1}")
print("----------------------")
user_input_2 = "Then, how many r's in blueberries? /no_think"
print(f"User: {user_input_2}")
response_2 = chatbot.generate_response(user_input_2)
print(f"Bot: {response_2}")
print("----------------------")
user_input_3 = "Really? /think"
print(f"User: {user_input_3}")
response_3 = chatbot.generate_response(user_input_3)
print(f"Bot: {response_3}")
⚠️ Important Note
For API compatibility, when enable_thinking=True
, regardless of whether the user uses /think
or /no_think
, the model will always output a block wrapped in <think>...</think>
. However, the content inside this block may be empty if thinking is disabled.
When enable_thinking=False
, the soft switches are not valid. Regardless of any /think
or /no_think
tags input by the user, the model will not generate think content and will not include a <think>...</think>
block.
Agentic Use
Qwen3 excels in tool calling capabilities. We recommend using Qwen-Agent to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
from qwen_agent.agents import Assistant
llm_cfg = {
'model': 'Qwen3-235B-A22B',
'model_server': 'http://localhost:8000/v1',
'api_key': 'EMPTY',
}
tools = [
{'mcpServers': {
'time': {
'command': 'uvx',
'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
},
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
},
'code_interpreter',
]
bot = Assistant(llm=llm_cfg, function_list=tools)
messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
for responses in bot.run(messages=messages):
pass
print(responses)
Processing Long Texts
Qwen3 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively. We have validated the model's performance on context lengths of up to 131,072 tokens using the YaRN method.
📄 License
This project is licensed under the Apache 2.0 License.