GPT-OSS

  • Original model weights.
  • Includes sizes for 20b.
  • Converted from the original vendored weights to gguf as bf16.
Downloads last month
57
GGUF
Model size
21B params
Architecture
gpt-oss
Hardware compatibility
Log In to add your hardware

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for teleprint-me/gpt-oss

Quantized
(175)
this model