ONNX flavor of https://huggingface.co/openai/gpt-oss-20b.
The ONNX model using int4 quantization.
When pinning embeddings to CPU it will run well on 12GB gpus.
- Downloads last month
- 18
Model tree for onnx-community/gpt-oss-20b-ONNX
Base model
openai/gpt-oss-20b