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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openai/gpt-oss-20b")
model = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-20b", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

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

vLLM

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

SGLang

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
```

gpt-oss community docs proposal: Harmony-aware local serving on Apple Silicon

#277

by Raullen - opened 5 days ago

Discussion

Raullen

5 days ago

Proposing a community local-serving note for gpt-oss-20b that explains Harmony handling rather than treating it as an ordinary text-only prompt template.

Rapid-MLX has dedicated Harmony reasoning/tool parsers and an output router. The suggested documentation would show model discovery and then require final-channel, tool-call and streaming checks with the pinned MXFP4/Q8 artifact. Tool invocations must remain distinguishable from visible answer content.

One limitation to disclose up front: our historical September Personal Intelligence harness scored this build 14/15 because one search/browse response used a Harmony citation rather than the required source URL. That product feature was retired in October; its old registration is not a current qualification. A new recipe should measure the current API path and avoid claiming generic agent reliability. No 120B or Safeguard behavior is inferred from this 20B proposal.

Concrete catalog entry: gpt-oss-20b → mlx-community/gpt-oss-20b-MXFP4-Q8@773a7da77e569019bb0fd17a554b263738d669a3. This is a conversion/distribution artifact; it is not presented as an official upstream release.

Source references (fixed Rapid commit): catalog, Harmony routing, Harmony tests, historical failed case.

Verification status: this proposal is based on reading the catalog, implementation and the linked documentation/tests. No fresh model inference or test-suite run was performed for this submission; source tests are not an end-to-end qualification. It requests a community documentation scope, not an official endorsement or a performance listing.

Disclosure: I maintain Rapid-MLX. Prepared with AI assistance under my direction. Anonymous usage-metadata telemetry is enabled by default; DO_NOT_TRACK=1 disables it. The original model and conversion terms continue to apply.

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