Modelpublic

amd/gemma-2-2b-onnx-ryzenai-1.7-hybrid

sourceHugging Facegemmaupdated 8mo agoView on Hugging Face

0likes

Model Card

amd/gemma-2-2b-onnx-ryzenai-1.7-hybrid

—## Introduction This model was created using Quark Quantization, followed by OGA Model Builder, and finalized with post-processing for NPU deployment.
—## Quantization Strategy
—AWQ / Group 128 / Asymmetric / BFP16 activations / UINT4 weights

—## Quick Start For quickstart, refer to Ryzen AI documentation

Evaluation scores

The MMLU scores are, astronomy: 53.29, philosophy: 56.91 and management: 68.93.

License

Modifications copyright(c) 2026 Advanced Micro Devices,Inc. All rights reserved.