openai
/

gpt-oss-20b

Text Generation

8-bit precision

Model card Files Files and versions

Instructions to use openai/gpt-oss-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openai/gpt-oss-20b with Transformers:

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

pipe = pipeline("text-generation", model="openai/gpt-oss-20b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-20b")
model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-20b")
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
Local Apps Settings

How to use openai/gpt-oss-20b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openai/gpt-oss-20b"
# 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-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openai/gpt-oss-20b

How to use openai/gpt-oss-20b 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-20b" \
    --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-20b",
		"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-20b" \
        --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-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openai/gpt-oss-20b with Docker Model Runner:
```
docker model run hf.co/openai/gpt-oss-20b
```

Resources

View closed (38)

i want a new model

#266 opened 1 day ago by

Still the undisputed best model for 16gb consumer cards, when can we expect a refresh / new model?

#265 opened 5 days ago by

Listed on OpenModelMap

#264 opened 11 days ago by

Add IFStruct v1.0 evaluation result

#263 opened 12 days ago by

Update README.md

#262 opened 12 days ago by

Update README.md

#261 opened 16 days ago by

Interesting work — mobile AI perspective

#260 opened 17 days ago by

GPT-OSS 20B — can it run on phones? We tested.

#259 opened 17 days ago by

Listed on OpenModelMap

#258 opened 24 days ago by

TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture

#257 opened about 1 month ago by

Add EvalEval community eval results

#256 opened about 1 month ago by

Add LEXam evaluation results

#255 opened about 1 month ago by

Delete original/model.safetensors

#254 opened 2 months ago by

abdullahsaad5555

our ideas

#253 opened 3 months ago by

my ideas

#252 opened 3 months ago by

Chat template drops intermediate thinking tokens

#251 opened 4 months ago by

Hello World

#249 opened 4 months ago by

Update special_tokens_map.json

#248 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#247 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#246 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#245 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#244 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#243 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#242 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#241 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#240 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#239 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#238 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#237 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#236 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#235 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#234 opened 4 months ago by

Add evaluation results from GPT-OSS paper

#233 opened 4 months ago by

My_gpt

#232 opened 5 months ago by

GPT-OSS-20B out-of-memory on g4dn.12xlarge (4x16GB VRAM)

#231 opened 5 months ago by

gpt-oss-120b reasoning token count

#230 opened 5 months ago by

Update chat_template.jinja

#229 opened 5 months ago by

If I modify the chat_template.jinja, can the model know the current time?

#228 opened 5 months ago by

Upload main.py

#227 opened 5 months ago by

Ananthusajeev190

Upload brain.cpython-312.pyc

#226 opened 5 months ago by

Ananthusajeev190

Guidance Needed: GPT-OSS 20B Fine-Tuning with Unsloth → GGUF → Ollama → Triton (vLLM / TensorRT-LLM)

#225 opened 6 months ago by

vvv

#224 opened 6 months ago by

Upload Saii.py

#223 opened 6 months ago by

Ananthusajeev190

Upload Sai.py

#222 opened 6 months ago by

Ananthusajeev190

Upload Saversai.ai.py

#221 opened 6 months ago by

Ananthusajeev190

Upload Saversai.py

#220 opened 6 months ago by

Ananthusajeev190

Upload model.safetensors

#219 opened 6 months ago by

Ananthusajeev190

Function call token ordering mismatch with Harmony format and chat template

#218 opened 6 months ago by

[Adding reasoning level in the prompt]

#217 opened 6 months ago by

Upload Ai_talk_internal_monologue .txt

#216 opened 6 months ago by

Ananthusajeev190