Instructions to use mlabonne/Qwen3-30B-A3B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlabonne/Qwen3-30B-A3B-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="mlabonne/Qwen3-30B-A3B-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlabonne/Qwen3-30B-A3B-abliterated")
model = AutoModelForCausalLM.from_pretrained("mlabonne/Qwen3-30B-A3B-abliterated")
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 mlabonne/Qwen3-30B-A3B-abliterated with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mlabonne/Qwen3-30B-A3B-abliterated

SGLang

How to use mlabonne/Qwen3-30B-A3B-abliterated 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 "mlabonne/Qwen3-30B-A3B-abliterated" \
    --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": "mlabonne/Qwen3-30B-A3B-abliterated",
		"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 "mlabonne/Qwen3-30B-A3B-abliterated" \
        --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": "mlabonne/Qwen3-30B-A3B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mlabonne/Qwen3-30B-A3B-abliterated with Docker Model Runner:
```
docker model run hf.co/mlabonne/Qwen3-30B-A3B-abliterated
```

mlabonne commited on Apr 30, 2025

Commit

bc6e36d

verified ·

1 Parent(s): cafe814

Upload Qwen3MoeForCausalLM

Browse files

Files changed (12) hide show

model-00001-of-00013.safetensors +1 -1
model-00002-of-00013.safetensors +1 -1
model-00003-of-00013.safetensors +1 -1
model-00004-of-00013.safetensors +1 -1
model-00005-of-00013.safetensors +1 -1
model-00006-of-00013.safetensors +1 -1
model-00007-of-00013.safetensors +1 -1
model-00008-of-00013.safetensors +1 -1
model-00009-of-00013.safetensors +1 -1
model-00010-of-00013.safetensors +1 -1
model-00011-of-00013.safetensors +1 -1
model-00012-of-00013.safetensors +1 -1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:217d73cdc894552caf959988208fae53d86cf72c840bd6667b6f3489ce1b2d56
 size 4997184968

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a20eab2101918ee26ab45692f828477a28f39d13cbcd0aea7d70b6fe2951da6f
 size 4997741608

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3166676ce0b968a89444e59b3f5240260442b0e5e95691f1808246740c38d16e
 size 4997742208

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e575bf66dd9fe93ac6a50834d95b70d1c048de93fa2400300ef1c439a991281f
 size 4997743184

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffeeabd98dc60d15999270380d75865430c5edcd39b31b8686be417586d5830a
 size 4997743184