Qwen

Qwen3-235B-A22B-Instruct-2507-FP8

README

License: apache-2.0

Highlights

We introduce the updated version of the Qwen3-235B-A22B-FP8 non-thinking mode, named Qwen3-235B-A22B-Instruct-2507-FP8, featuring the following key enhancements:

Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage.
Substantial gains in long-tail knowledge coverage across multiple languages.
Markedly better alignment with user preferences in subjective and open-ended tasks, enabling more helpful responses and higher-quality text generation.
Enhanced capabilities in 256K long-context understanding.

image/jpeg

Model Overview

This repo contains the FP8 version of Qwen3-235B-A22B-Instruct-2507, which has the following features:

Type: Causal Language Models
Training Stage: Pretraining & Post-training
Number of Parameters: 235B in total and 22B activated
Number of Paramaters (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: 262,144 natively.

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.

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub, and Documentation.

Performance

Table with columns: Deepseek-V3-0324, GPT-4o-0327, Claude Opus 4 Non-thinking, Kimi K2, Qwen3-235B-A22B Non-thinking, Qwen3-235B-A22B-Instruct-2507
	Deepseek-V3-0324	GPT-4o-0327	Claude Opus 4 Non-thinking	Kimi K2	Qwen3-235B-A22B Non-thinking	Qwen3-235B-A22B-Instruct-2507
Knowledge
MMLU-Pro	81.2	79.8	86.6	81.1	75.2

*: For reproducibility, we report the win rates evaluated by GPT-4.1.

#: Results were generated using GPT-4o-20241120, as access to the native function calling API of GPT-4o-0327 was unavailable.

Quickstart

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:

markdown
KeyError: 'qwen3_moe'

The following contains a code snippet illustrating how to use the model generate content based on given inputs.

python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
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,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=16384
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

content = tokenizer.decode(output_ids, skip_special_tokens=True)

print("content:", content)

For deployment, you can use sglang>=0.4.6.post1 or vllm>=0.8.5 or to create an OpenAI-compatible API endpoint:

SGLang:

shell
python -m sglang.launch_server --model-path Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 --tp 4 --context-length 262144

vLLM:

shell
vllm serve Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 --tensor-parallel-size 4 --max-model-len 262144

Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value, such as 32,768.

For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.

Note on FP8

For convenience and performance, we have provided fp8-quantized model checkpoint for Qwen3, whose name ends with -FP8. The quantization method is fine-grained fp8 quantization with block size of 128. You can find more details in the quantization_config field in config.json.

You can use the Qwen3-235B-A22B-Instruct-2507-FP8 model with serveral inference frameworks, including transformers, sglang, and vllm, as the original bfloat16 model. However, please pay attention to the following known issues:

transformers:
- there are currently issues with the "fine-grained fp8" method in transformers for distributed inference. You may need to set the environment variable CUDA_LAUNCH_BLOCKING=1 if multiple devices are used in inference.

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.

python
from qwen_agent.agents import Assistant

# Define LLM
llm_cfg = {
    'model': 'Qwen3-235B-A22B-Instruct-2507-FP8',

    # Use a custom endpoint compatible with OpenAI API:
    'model_server': 'http://localhost:8000/v1',  # api_base
    'api_key': 'EMPTY',
}

# Define Tools
tools = [
    {'mcpServers': {  # You can specify the MCP configuration file
            'time': {
                'command': 'uvx',
                'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
            },
            "fetch": {
                "command": "uvx",
                "args": ["mcp-server-fetch"]
            }
        }
    },
  'code_interpreter',  # Built-in tools
]

# Define Agent
bot = Assistant(llm=llm_cfg, function_list=tools)

# Streaming generation
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)

Best Practices

To achieve optimal performance, we recommend the following settings:

Sampling Parameters:
- We suggest using Temperature=0.7, TopP=0.8, TopK=20, and MinP=0.
- For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
Adequate Output Length: We recommend using an output length of 16,384 tokens for most queries, which is adequate for instruct models.
Standardize Output Format: We recommend using prompts to standardize model outputs when benchmarking.
- Math Problems: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
- : Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the field with only the choice letter, e.g., ."

Citation

If you find our work helpful, feel free to give us a cite.

markdown
@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider