Qwen3-Next-80B-A3B-Thinking-GGUF

Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI).
We are excited to share our latest advancements in addressing these demands, centered on improving scaling efficiency through innovative model architecture.
We call this next-generation foundation models Qwen3-Next.

Highlights

Qwen3-Next-80B-A3B is the first installment in the Qwen3-Next series and features the following key enchancements:

• Hybrid Attention: Replaces standard attention with the combination of Gated DeltaNet and Gated Attention, enabling efficient context modeling for ultra-long context length.
• High-Sparsity Mixture-of-Experts (MoE): Achieves an extreme low activation ratio in MoE layers, drastically reducing FLOPs per token while preserving model capacity.
• Stability Optimizations: Includes techniques such as zero-centered and weight-decayed layernorm, and other stabilizing enhancements for robust pre-training and post-training.
• Multi-Token Prediction (MTP): Boosts pretraining model performance and accelerates inference.

We are seeing strong performance in terms of both parameter efficiency and inference speed for Qwen3-Next-80B-A3B:

• 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.
• Leveraging GSPO, we have addressed the stability and efficiency challenges posed by the hybrid attention mechanism combined with a high-sparsity MoE architecture in RL training.

!Qwen3-Next-80B-A3B-Thinking Benchmark Comparison

For more details, please refer to our blog post Qwen3-Next.

Model Overview

[!Note]

Qwen3-Next-80B-A3B-Thinking supports only thinking mode.

To enforce model thinking, the default chat template automatically includes .

Therefore, it is normal for the model's output to contain only without an explicit opening tag.

[!Note]

Qwen3-Next-80B-A3B-Thinking may generate thinking content longer than its predecessor.

We strongly recommend its use in highly complex reasoning tasks.

Qwen3-Next-80B-A3B-Thinking has the following features:

• 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
• Hidden Dimension: 2048
• Number of Layers: 48

• Gated Attention:

• Gated DeltaNet:

• Mixture of Experts:

• Context Length: 262,144 natively and extensible up to 1,010,000 tokens

Performance

Quickstart

llama.cpp

Check out our llama.cpp documentation for more usage guide.

We advise you to clone llama.cpp and install it following the official guide. We follow the latest version of llama.cpp.
In the following demonstration, we assume that you are running commands under the repository llama.cpp.

./llama-cli -hf Qwen/Qwen3-Next-80B-A3B-Thinking-GGUF:Q8_0 --jinja --color -ngl 99 -fa on -sm row --temp 0.6 --top-k 20 --top-p 0.95 --min-p 0 --presence-penalty 1.5 -c 262144 -n 256000 --no-context-shift

Processing Long Texts

Qwen3 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 131,072 tokens using the YaRN method.

To enable YARN in `llama.cpp:

./llama-cli ... -c 1010000 --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 262144

from qwen_agent.agents import Assistant


Define LLM
Using Alibaba Cloud Model Studio
llm_cfg = {
    'model': 'Qwen3-Next-80B-A3B-Thinking',
    'modeltype': 'qwendashscope',
}

Using OpenAI-compatible API endpoint. It is recommended to disable the reasoning and the tool call parsing
functionality of the deployment frameworks and let Qwen-Agent automate the related operations. For example, 
vllm serve Qwen/Qwen3-Next-80B-A3B-Thinking --served-model-name Qwen3-Next-80B-A3B-Thinking --port 8000 --tensor-parallel-size 4 --max-model-len 262144.

#
llm_cfg = {
    'model': 'Qwen3-Next-80B-A3B-Thinking',
# 
    # Use a custom endpoint compatible with OpenAI API:
    'modelserver': 'http://localhost:8000/v1',  # apibase without reasoning and tool call parsing
    'api_key': 'EMPTY',
    'generate_cfg': {
        'thoughtincontent': True,
    },
}

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=llmcfg, functionlist=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)

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:

{
        ...,
        "rope_scaling": {
            "rope_type": "yarn",
            "factor": 4.0,
            "originalmaxposition_embeddings": 262144
        }
    }

For vllm, you can use


VLLMALLOWLONGMAXMODELLEN=1 vllm serve ... --rope-scaling '{"ropetype":"yarn","factor":4.0,"originalmaxposition_embeddings":262144}' --max-model-len 1010000

For sglang, you can use


SGLANGALLOWOVERWRITELONGERCONTEXTLEN=1 python -m sglang.launchserver ... --json-model-override-args '{"ropescaling":{"ropetype":"yarn","factor":4.0,"originalmaxposition_embeddings":262144}}' --context-length 1010000

[!NOTE]

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.

1. No Thinking Content in History: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.

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}
}