dicksondickson/gpt-oss-20b-oQ8e-bf16-MLX
Updated Oct 24, 2026: Re-quantized with oMLX 0.7.3.dev2 with improved oQe Quantization and Better Low-Bit oQ. Please re-download if you have an earlier copy.
This model is a quantization of:
https://huggingface.co/openai/gpt-oss-20b
This model was quantized using oQ (oMLX 0.7.3.dev2) imatrix, mixed-precision quantization with Better Low-Bit oQ.
Important tensors are left at bf16 which is for Apple M3 chips and later.
Run the model using oMLX:
https://github.com/jundot/omlx
- Downloads last month
- 537
Model size
21B params
Tensor type
U32
·
BF16 ·
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for dicksondickson/gpt-oss-20b-oQ8e-bf16-MLX
Base model
openai/gpt-oss-20b