Instructions to use Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE

SGLang

How to use Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE with Docker Model Runner:
```
docker model run hf.co/Doctor-Shotgun/Qwen3-Coder-30B-A3B-Instruct-ScatterMoE
```

Qwen3-Coder-30B-A3B-Instruct-ScatterMoE

Re-packed weights of Qwen/Qwen3-Coder-30B-A3B-Instruct using Charles Goddard's remote code implementation of scattermoe, including scripts to convert to and from standard Qwen3MoeForCausalLM. Thank you to intervitens for assistance with memory-efficient conversion scripts!

This is intended to be used as a drop-in replacement for efficient training using any transformers-based training repository.

Optional monkeypatches included for Liger Kernel and Cut Cross-Entropy. Simply rename the relevant modeling file to modeling_qwen3_shared_moe.py.

Citations

@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}, 
}

@misc{tan2024scatteredmixtureofexpertsimplementation,
      title={Scattered Mixture-of-Experts Implementation}, 
      author={Shawn Tan and Yikang Shen and Rameswar Panda and Aaron Courville},
      year={2024},
      eprint={2403.08245},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2403.08245}, 
}

@misc{hsu2025ligerkernelefficienttriton,
      title={Liger Kernel: Efficient Triton Kernels for LLM Training}, 
      author={Pin-Lun Hsu and Yun Dai and Vignesh Kothapalli and Qingquan Song and Shao Tang and Siyu Zhu and Steven Shimizu and Shivam Sahni and Haowen Ning and Yanning Chen},
      year={2025},
      eprint={2410.10989},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2410.10989}, 
}

@misc{wijmans2025cutlosseslargevocabularylanguage,
      title={Cut Your Losses in Large-Vocabulary Language Models}, 
      author={Erik Wijmans and Brody Huval and Alexander Hertzberg and Vladlen Koltun and Philipp Krähenbühl},
      year={2025},
      eprint={2411.09009},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2411.09009}, 
}