Downloads · 30 days
50.6K
4% of all-time downloads
gpt-oss-20b-bf16
lmsys/gpt-oss-20b-bf16
gpt-oss-20b-bf16 is a machine learning model from lmsys. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is the bf16 version converted from openai/gpt-oss-20b. You can use this model in SGLang with the following instructions.
All-time downloads
1.2M
Public
Parameters
20.9B
22.7 GB on disk
Likes
11
Public
Repo makeup
Click a slice to open those files.
.safetensors22.7 GB · 100%
Parameter types
How the weights are stored.
F8_E5M219.1B · 91%
Model card
From the Hugging Face model README
gpt-oss-20b-bf16
Model Introduction
This model is the bf16 version converted from openai/gpt-oss-20b.
Usage
You can use this model in SGLang with the following instructions.
Installation
# build from source
git clone https://github.com/sgl-project/sglang
cd sglang
pip3 install pip --upgrade
pip3 install -e "python[all]"
# ROCm 6.3
pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/rocm6.3
git clone https://github.com/triton-lang/triton
cd python/triton_kernels
pip3 install .
# hopper
pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu126
pip3 install sgl-kernel==0.3.2
# blackwell cu128
pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu128
pip3 install https://github.com/sgl-project/whl/releases/download/v0.3.2/sgl_kernel-0.3.2+cu128-cp39-abi3-manylinux2014_x86_64.whl
# blackwell cu129
pip3 install torch==2.8.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/test/cu129
pip3 install https://github.com/sgl-project/whl/releases/download/v0.3.2/sgl_kernel-0.3.2-cp39-abi3-manylinux2014_x86_64.whl
Launch command
python3 -m sglang.launch_server --model lmsys/gpt-oss-20b-bf16
For more details
- Type
- gpt_oss
- Created
- Aug 5, 2025
- Updated
- Aug 18, 2025