README.md

metadata

language:
  - en
base_model:
  - openai/gpt-oss-20b
  - unsloth/gpt-oss-20b-BF16
pipeline_tag: text-generation
tags:
  - gpt_oss
  - vllm
  - fp8
  - conversational
  - compressed-tensors
  - text-generation-inference
license: apache-2.0
license_name: apache-2.0
name: RedHatAI/gpt-oss-20b-FP8-Dynamic
description: >-
  This model was obtained by quantizing the weights and activations to FP8 data
  type. It is based on the gpt-oss-20b-BF16 architecture.
readme: https://huggingface.co/RedHatAI/gpt-oss-20b-FP8-Dynamic/main/README.md
tasks:
  - text-to-text
  - text-generation
provider: OpenAI
license_link: https://www.apache.org/licenses/LICENSE-2.0

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.