Instructions to use ArliAI/gpt-oss-120b-Derestricted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArliAI/gpt-oss-120b-Derestricted with Transformers:

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

pipe = pipeline("text-generation", model="ArliAI/gpt-oss-120b-Derestricted")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArliAI/gpt-oss-120b-Derestricted")
model = AutoModelForCausalLM.from_pretrained("ArliAI/gpt-oss-120b-Derestricted")
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 ArliAI/gpt-oss-120b-Derestricted with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArliAI/gpt-oss-120b-Derestricted"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArliAI/gpt-oss-120b-Derestricted",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ArliAI/gpt-oss-120b-Derestricted

SGLang

How to use ArliAI/gpt-oss-120b-Derestricted 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 "ArliAI/gpt-oss-120b-Derestricted" \
    --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": "ArliAI/gpt-oss-120b-Derestricted",
		"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 "ArliAI/gpt-oss-120b-Derestricted" \
        --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": "ArliAI/gpt-oss-120b-Derestricted",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ArliAI/gpt-oss-120b-Derestricted with Docker Model Runner:
```
docker model run hf.co/ArliAI/gpt-oss-120b-Derestricted
```

Weight size and VRAM usage much more than the original model

by SteveImmanuel - opened Dec 5, 2025

Discussion

SteveImmanuel

Dec 5, 2025

Hi, your model seems to handle better in not refusing request. I am curious, however, why your final weights are much bigger than the original gpt-oss-120b. Is it because unquantized or maybe your approach does indeed require storing more weights? Thanks

WyattTheSkid

Dec 13, 2025

If you quantize it to mxfp4 yourself you shouldn’t have any problems with that

radna0

Feb 11

Anyone got mxfp4 of this model? Not gguf I mean.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment