ONNX Model Zoo

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

By amd · ↓ 0 · ♥ 0 · Updated 2026-01-26

What's in this repo

This page lists the files in amd/gemma-2-2b-onnx-ryzenai-1.7-hybrid, including model_jit.onnx.

  • 1 ONNX models (.onnx files)
  • 12 files, including 5 .json, 2 .bin, 1 .md, 1 .onnx, 1 .data, 1 .model
  • Last updated 2026-01-26

ONNX files

File Size Download
model_jit.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

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.

Model info

onnx zh en base_model:google/gemma-2-2b base_model:quantized:google/gemma-2-2b license:gemma region:us
↓ 0 ♥ 0

Created: 2026-01-22

Updated: 2026-01-26

View on Hugging Face

Files (12)

.gitattributes
README.md
genai_config.json
genai_config_bkp.json
model_jit.bin
model_jit.onnx ONNX
model_jit.onnx.data
model_jit.pb.bin
special_tokens_map.json
tokenizer.json
tokenizer.model
tokenizer_config.json

Related models

More from amd

More models

No task type declared.

Popular models