openai
/

gpt-oss-120b

Text Generation

8-bit precision

Model card Files Files and versions

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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-120b")
model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-120b", device_map="auto")
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]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
AMD Developer Cloud
Local Apps Settings

How to use openai/gpt-oss-120b with vLLM:

Install from pip and serve model

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

Use Docker

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

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

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

Resources

View closed (40)

Add evaluation results from GPT-OSS paper

#178 opened 5 months ago by

Add SWE-Bench Pro evaluation results

#177 opened 5 months ago by

Upload Infex.py

#176 opened 6 months ago by

Ananthusajeev190

Upload 9 files

#175 opened 6 months ago by

Ananthusajeev190

Upload main.py

#174 opened 6 months ago by

Ananthusajeev190

Inquiry About Military Use and Restrictions for US and Allied Nations

#173 opened 6 months ago by

Upload 6 files

#172 opened 7 months ago by

Ananthusajeev190

Upload 5 files

#171 opened 7 months ago by

Ananthusajeev190

Upload 312 files

#170 opened 7 months ago by

Ananthusajeev190

If tool.description is null, it will trigger exception

#169 opened 7 months ago by

ClosedAI: MXFP4 is not Open Source

#168 opened 7 months ago by

Create configfars_prompt.txt

#167 opened 7 months ago by

Create configfars_prompt.txt

#166 opened 7 months ago by

Request: Tensor alignment (256) for llama.cpp quantization

#165 opened 8 months ago by

can i load the local model without internet?

#164 opened 8 months ago by

Add Artificial Analysis evaluations for gpt-oss-120b

#162 opened 8 months ago by

Please move metal/ and original/ folder in a separate branch

#160 opened 8 months ago by

How many graphics cards are needed to train OSS-120B using GRPO?

#158 opened 8 months ago by

gpt-weights

#157 opened 8 months ago by

Suggesting an open-weight Gpt-Oss LLM between the 20B and 120B parameters

#156 opened 9 months ago by

Trouble using GPT-OSS 120B via MCP (repro + logs inside)

#155 opened 9 months ago by

Small changes in readme for Vllm serve

#154 opened 9 months ago by

RuntimeError: expected scalar type Float but found BFloat16 during activation capture

#153 opened 9 months ago by

An error occurred when generating a response.

#152 opened 9 months ago by

Parallel Tool Calling not working in latest commit

#151 opened 9 months ago by

GPT-OSS 120B

#150 opened 9 months ago by

Reinforcement Learning example

#148 opened 10 months ago by

So much censorship!

#147 opened 10 months ago by

An infinitty max input tokenizer token length

#146 opened 10 months ago by

mlp

#145 opened 10 months ago by

Update README.md

#143 opened 10 months ago by

gpt-oss-120b

#141 opened 11 months ago by

Issue with tokenizer_config.json

#140 opened 11 months ago by

Failed in vllm inference

#139 opened 11 months ago by

Update README.md

#137 opened 11 months ago by

gpt-oss 120b AMD GPU output problem

#136 opened 11 months ago by

Update Readme.md add multilingual language tag

#135 opened 11 months ago by

Can gpt-oss support local deployment on V100 GPU?

#134 opened 11 months ago by

gpt-oss-120b has high possibility to generate response as part of reasoning

#133 opened 11 months ago by

AIME eval script does not score correctly some answers

#132 opened 11 months ago by

Is it possible to use fine tuning on this model?

#131 opened 11 months ago by

assistantfinal, analysis keyword is contained in the huggingface gpt-oss-120 output. Is this intended?

#130 opened 11 months ago by

123

#129 opened 11 months ago by

Rename README.md to làm đẹp đoạn code của tôi được không ? tôi sẽ dán vào đây

#128 opened 11 months ago by

How to deploy gpt oss 120B in Openshift AI platform

#126 opened 11 months ago by

how to run gpt-oss-120b by ollama using multi-gpu

#125 opened 11 months ago by

Is this demo powered by hugging face?

#124 opened 11 months ago by

Very bad censorship

#123 opened 12 months ago by

how to exclude file in "original" folder while model download

#122 opened 12 months ago by

gpt-oss-120b works with OpenRouter + MCP servers, but not with locally hosted setup via LibreChat

#121 opened 12 months ago by