RedHatAI/gpt-oss-20b-FP8-Dynamic

Model Overview

  • Model Architecture: gpt-oss-20b-BF16
    • Input: Text
    • Output: Text
  • Model Optimizations:
    • Weight quantization: FP8
    • Activation quantization: FP8
  • Release Date: 08/13/2025
  • Version: 1.0
  • Model Developers: RedHatAI

Quantized version of unsloth/gpt-oss-20b-BF16.

Downloads last month
5,903
Safetensors
Model size
20.9B params
Tensor type
F32
·
BF16
·
F8_E4M3
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for RedHatAI/gpt-oss-20b-FP8-Dynamic

Base model

openai/gpt-oss-20b
Quantized
(3)
this model