Instructions to use tiny-random/qwen3-next-moe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/qwen3-next-moe with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/qwen3-next-moe")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tiny-random/qwen3-next-moe")
model = AutoModelForCausalLM.from_pretrained("tiny-random/qwen3-next-moe")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiny-random/qwen3-next-moe with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/qwen3-next-moe"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/qwen3-next-moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/qwen3-next-moe

SGLang

How to use tiny-random/qwen3-next-moe 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 "tiny-random/qwen3-next-moe" \
    --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": "tiny-random/qwen3-next-moe",
		"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 "tiny-random/qwen3-next-moe" \
        --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": "tiny-random/qwen3-next-moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/qwen3-next-moe with Docker Model Runner:
```
docker model run hf.co/tiny-random/qwen3-next-moe
```

yujiepan commited on Sep 12, 2025

Commit

fab38e0

verified ·

1 Parent(s): f1b9c0f

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

README.md +1 -0
model.safetensors +2 -2

README.md CHANGED Viewed

@@ -132,6 +132,7 @@ model.mtp = nn.ModuleDict({
     "pre_fc_norm_hidden": nn.RMSNorm(config.hidden_size),
     "layers": nn.ModuleList([deepcopy(model.model.layers[3])]),
 })
 set_seed(42)
 with torch.no_grad():
     for name, p in sorted(model.named_parameters()):

     "pre_fc_norm_hidden": nn.RMSNorm(config.hidden_size),
     "layers": nn.ModuleList([deepcopy(model.model.layers[3])]),
 })
+model = model.to(torch.bfloat16)
 set_seed(42)
 with torch.no_grad():
     for name, p in sorted(model.named_parameters()):

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe4378d59f21cb212c6ca10786e64c4bea327f62dbfc93b2f42c83962a80912b
-size 5740672

 version https://git-lfs.github.com/spec/v1
+oid sha256:2180e924c4cba5f5933a53d1f03e258a58ddfba8ff6d7bfdd0b8560811500f7d
+size 5740400