Qwen3-Next-80B-A3B-Instruct - 诺德美地科技

在过去的几个月里，我们观察到一个越来越清晰的趋势，即在追求更强大和代理型人工智能（AI）的过程中，总体参数和上下文长度都在不断扩展。我们很高兴分享我们在应对这些需求方面的最新进展，其核心是通过创新的模型架构来提高扩展效率。我们称之为下一代基础模型 Qwen3-Next。

亮点:

Qwen3-Next-80B-A3B是Qwen3-Next系列的第一款产品，具有以下关键增强功能：

Hybrid Attention: 将标准注意力机制替换为Gated DeltaNet和Gated Attention的组合，实现超长上下文长度的有效上下文建模。
High-Sparsity Mixture-of-Experts (MoE): 在MoE层中实现极低的激活比率，显著减少每个token的FLOPs，同时保持模型容量。
Stability Optimizations:包括零中心化和权重衰减归一化等技术，以及其他用于鲁棒预训练和后训练的稳定增强技术。
Multi-Token Prediction (MTP): 提升预训练模型性能并加速推理。

我们看到Qwen3-Next-80B-A3B在参数效率和推理速度方面都表现出色：

Qwen3-Next-80B-A3B-Base outperforms Qwen3-32B-Base on downstream tasks with 10% of the total training cost and with 10 times inference throughput for context over 32K tokens.
Qwen3-Next-80B-A3B-Instruct performs on par with Qwen3-235B-A22B-Instruct-2507 on certain benchmarks, while demonstrating significant advantages in handling ultra-long-context tasks up to 256K tokens.

关于更多详情，请参考我们的博客文章Qwen3-Next。

模型概述

Qwen3-Next-80B-A3B-Instruct仅支持指令（非思考）模式，并且在输出中不生成<think></think>块。

Qwen3-Next-80B-A3B-Instruct 具有以下功能：

Type: Causal Language Models
Training Stage: Pretraining (15T tokens) & Post-training
Number of Parameters: 80B in total and 3B activated
Number of Paramaters (Non-Embedding): 79B
Number of Layers: 48
Hidden Dimension: 2048
Hybrid Layout: 12 * (3 * (Gated DeltaNet -> MoE) -> (Gated Attention -> MoE))
Gated Attention:
- Number of Attention Heads: 16 for Q and 2 for KV
- Head Dimension: 256
- Rotary Position Embedding Dimension: 64
Gated DeltaNet:
- Number of Linear Attention Heads: 32 for V and 16 for QK
- Head Dimension: 128
Mixture of Experts:
- Number of Experts: 512
- Number of Activated Experts: 10
- Number of Shared Experts: 1
- Expert Intermediate Dimension: 512
Context Length: 262,144 natively and extensible up to 1,010,000 tokens

Performance

	Qwen3-30B-A3B-Instruct-2507	Qwen3-32B Non-Thinking	Qwen3-235B-A22B-Instruct-2507	Qwen3-Next-80B-A3B-Instruct
Knowledge
MMLU-Pro	78.4	71.9	83.0	80.6
MMLU-Redux	89.3	85.7	93.1	90.9
GPQA	70.4	54.6	77.5	72.9
SuperGPQA	53.4	43.2	62.6	58.8
Reasoning
AIME25	61.3	20.2	70.3	69.5
HMMT25	43.0	9.8	55.4	54.1
LiveBench 20241125	69.0	59.8	75.4	75.8
Coding
LiveCodeBench v6 (25.02-25.05)	43.2	29.1	51.8	56.6
MultiPL-E	83.8	76.9	87.9	87.8
Aider-Polyglot	35.6	40.0	57.3	49.8
Alignment
IFEval	84.7	83.2	88.7	87.6
Arena-Hard v2*	69.0	34.1	79.2	82.7
Creative Writing v3	86.0	78.3	87.5	85.3
WritingBench	85.5	75.4	85.2	87.3
Agent
BFCL-v3	65.1	63.0	70.9	70.3
TAU1-Retail	59.1	40.1	71.3	60.9
TAU1-Airline	40.0	17.0	44.0	44.0
TAU2-Retail	57.0	48.8	74.6	57.3
TAU2-Airline	38.0	24.0	50.0	45.5
TAU2-Telecom	12.3	24.6	32.5	13.2
Multilingualism
MultiIF	67.9	70.7	77.5	75.8
MMLU-ProX	72.0	69.3	79.4	76.7
INCLUDE	71.9	70.9	79.5	78.9
PolyMATH	43.1	22.5	50.2	45.9

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

Quickstart

The code for Qwen3-Next has been merged into the main branch of Hugging Face transformers.

pip install git+https://github.com/huggingface/transformers.git@main

With earlier versions, you will encounter the following error:

KeyError: 'qwen3_next'

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

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen3-Next-80B-A3B-Instruct"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    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)

Multi-Token Prediction (MTP) is not generally available in Hugging Face Transformers.

The efficiency or throughput improvement depends highly on the implementation. It is recommended to adopt a dedicated inference framework, e.g., SGLang and vLLM, for inference tasks.

Depending on the inference settings, you may observe better efficiency with flash-linear-attention and causal-conv1d. See the above links for detailed instructions and requirements.

Deployment

For deployment, you can use the latest sglang or vllm to create an OpenAI-compatible API endpoint.

SGLang

SGLang is a fast serving framework for large language models and vision language models. SGLang could be used to launch a server with OpenAI-compatible API service.

SGLang has supported Qwen3-Next in its main branch, which can be installed from source:

pip install 'sglang[all] @ git+https://github.com/sgl-project/sglang.git@main#subdirectory=python'

The following command can be used to create an API endpoint at http://localhost:30000/v1 with maximum context length 256K tokens using tensor parallel on 4 GPUs.

SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Instruct --port 30000 --tp-size 4 --context-length 262144 --mem-fraction-static 0.8

The following command is recommended for MTP with the rest settings the same as above:

SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server --model-path Qwen/Qwen3-Next-80B-A3B-Instruct --port 30000 --tp-size 4 --context-length 262144 --mem-fraction-static 0.8 --speculative-algo NEXTN --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4

The environment variable SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 is required at the moment.

The default context length is 256K. Consider reducing the context length to a smaller value, e.g., 32768, if the server fail to start.

vLLM

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. vLLM could be used to launch a server with OpenAI-compatible API service.

vLLM has supported Qwen3-Next in its main branch, which can be installed from source:

pip install vllm --pre --extra-index-url https://wheels.vllm.ai/nightly

The following command can be used to create an API endpoint at http://localhost:8000/v1 with maximum context length 256K tokens using tensor parallel on 4 GPUs.

VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --port 8000 --tensor-parallel-size 4 --max-model-len 262144

The following command is recommended for MTP with the rest settings the same as above:

VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve Qwen/Qwen3-Next-80B-A3B-Instruct --port 8000 --tensor-parallel-size 4 --max-model-len 262144 --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'

The environment variable VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 is required at the moment.

The default context length is 256K. Consider reducing the context length to a smaller value, e.g., 32768, if the server fail to start.

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

# Define LLM
llm_cfg = {
    'model': 'Qwen3-Next-80B-A3B-Instruct',

    # 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)

Processing Ultra-Long Texts

Qwen3-Next natively supports context lengths of up to 262,144 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 1 million tokens using the YaRN method.

YaRN is currently supported by several inference frameworks, e.g., transformers, vllm and sglang. In general, there are two approaches to enabling YaRN for supported frameworks:

Modifying the model files: In the config.json file, add the rope_scaling fields:{ ..., "rope_scaling": { "rope_type": "yarn", "factor": 4.0, "original_max_position_embeddings": 262144 } }
Passing command line arguments:For vllm, you can useVLLM_ALLOW_LONG_MAX_MODEL_LEN=1 vllm serve ... --rope-scaling '{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":262144}' --max-model-len 1010000 For sglang, you can useSGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1 python -m sglang.launch_server ... --json-model-override-args '{"rope_scaling":{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":262144}}' --context-length 1010000

All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, potentially impacting performance on shorter texts. We advise adding the rope_scaling configuration only when processing long contexts is required. It is also recommended to modify the factor as needed. For example, if the typical context length for your application is 524,288 tokens, it would be better to set factor as 2.0.

Long-Context Performance

We test the model on an 1M version of the RULER benchmark.

Model Name	Acc avg	4k	8k	16k	32k	64k	96k	128k	192k	256k	384k	512k	640k	768k	896k	1000k
Qwen3-30B-A3B-Instruct-2507	86.8	98.0	96.7	96.9	97.2	93.4	91.0	89.1	89.8	82.5	83.6	78.4	79.7	77.6	75.7	72.8
Qwen3-235B-A22B-Instruct-2507	92.5	98.5	97.6	96.9	97.3	95.8	94.9	93.9	94.5	91.0	92.2	90.9	87.8	84.8	86.5	84.5
Qwen3-Next-80B-A3B-Instruct	91.8	98.5	99.0	98.0	98.7	97.6	95.0	96.0	94.0	93.5	91.7	86.9	85.5	81.7	80.3	80.3

Qwen3-Next are evaluated with YaRN enabled. Qwen3-2507 models are evaluated with Dual Chunk Attention enabled.
Since the evaluation is time-consuming, we use 260 samples for each length (13 sub-tasks, 20 samples for each).

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.
- Multiple-Choice Questions: Add the following JSON structure to the prompt to standardize responses: “Please show your choice in the answer field with only the choice letter, e.g., "answer": "C".”

Citation

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

@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}, 
}

@article{qwen2.5-1m,
      title={Qwen2.5-1M Technical Report}, 
      author={An Yang and Bowen Yu and Chengyuan Li and Dayiheng Liu and Fei Huang and Haoyan Huang and Jiandong Jiang and Jianhong Tu and Jianwei Zhang and Jingren Zhou and Junyang Lin and Kai Dang and Kexin Yang and Le Yu and Mei Li and Minmin Sun and Qin Zhu and Rui Men and Tao He and Weijia Xu and Wenbiao Yin and Wenyuan Yu and Xiafei Qiu and Xingzhang Ren and Xinlong Yang and Yong Li and Zhiying Xu and Zipeng Zhang},
      journal={arXiv preprint arXiv:2501.15383},
      year={2025}
}

原创文章，转载请注明： 转载自诺德美地科技

本文链接地址: Qwen3-Next-80B-A3B-Instruct