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

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
```

CUDA out of memory issues when running gptoss model on colab T4

#99

by sumeetm - opened Aug 9, 2025

Discussion

sumeetm

Aug 9, 2025

Trying to run gptoss-20B on T4 colab, facing below memory issue, was anyone able to resolve this?

Loading checkpoint shards:   0%
 0/3 [00:00<?, ?it/s]
---------------------------------------------------------------------------
OutOfMemoryError                          Traceback (most recent call last)
/tmp/ipython-input-2717120482.py in <cell line: 0>()
      4 
      5 tokenizer = AutoTokenizer.from_pretrained(model_id)
----> 6 model = AutoModelForCausalLM.from_pretrained(
      7     model_id,
      8     torch_dtype="auto",
9 frames
/usr/local/lib/python3.11/dist-packages/transformers/integrations/mxfp4.py in convert_moe_packed_tensors(blocks, scales, dtype, rows_per_chunk)
    121 
    122         # nibble indices -> int64
--> 123         idx_lo = (blk & 0x0F).to(torch.long)
    124         idx_hi = (blk >> 4).to(torch.long)
    125 

OutOfMemoryError: CUDA out of memory. Tried to allocate 1.98 GiB. GPU 0 has a total capacity of 14.74 GiB of which 1.47 GiB is free. Process 7925 has 13.27 GiB memory in use. Of the allocated memory 11.95 GiB is allocated by PyTorch, and 1.21 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)

Have tried below things to free up memory still no luck

import os
os.environ["PYTORCH_CUDA_ALLOC_CONF"]="expandable_segments:True"

import gc
torch.cuda.empty_cache()
gc.collect()

sachin6624

Aug 13, 2025

It won't work, because "openai/gpt-oss-20b" requires atleast 16GB GPU and you need to use atleast L4 GPU, if you are using colab. T4 only have 15GB GPU.
Read this link carefully :

https://openai.com/index/introducing-gpt-oss/#:~:text=The%20gpt%2Doss%2D20b%20model%20delivers%20similar%20results%20to%20OpenAI%20o3%E2%80%91mini%20on%20common%20benchmarks%20and%20can%20run%20on%20edge%20devices%20with%20just%2016%20GB%20of%20memory%2C%20making%20it%20ideal%20for%20on%2Ddevice%20use%20cases

entfane

Aug 21, 2025

@sumeetm @sachin6624 You can make it run in colab with the help of this

!pip install -q --upgrade torch
!pip install -q git+https://github.com/huggingface/transformers triton==3.4 git+https://github.com/triton-lang/triton.git@main#subdirectory=python/triton_kernels
!pip uninstall -q torchvision torchaudio -y

Restart and then you can load the model

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