Skip to main content

Ctrl+K

Quark Version List

GitHub
Support

AMD Quark 0.11 documentation

Release Notes

Release Information

Getting Started with AMD Quark

Introduction to Quantization
Installation
Getting started: Introduction
Getting started: Quark for ONNX
Getting started: Quark for PyTorch
PyTorch Examples
ONNX Examples

Supported accelerators

AMD Ryzen AI
AMD Instinct
- Language Model Post Training Quantization (PTQ) Using Quark
  - FP4 Post Training Quantization (PTQ) for LLM models
  - FP8 Post Training Quantization (PTQ) for LLM models
- Evaluation of Quantized Models

Advanced AMD Quark Features for PyTorch

Configuring PyTorch Quantization for Large Language Models
Configuring PyTorch Quantization from Scratch
Save and Load Quantized Models
Exporting Quantized Models
Best Practices for Post-Training Quantization (PTQ)
Debugging quantization Degradation
Language Model Optimization
Activation/Weight Smoothing (SmoothQuant)
Auto SmoothQuant
Activation-aware Weight Quantization (AWQ)
- AWQ end-to-end demo
Block Floating Point 16
Extensions
- Integration with AMD Pytorch-light (APL)
- Brevitas Integration
Using MX (Microscaling)
Two Level Quantization Formats

Advanced Quark Features for ONNX

Configuring ONNX Quantization
Data and OP Types
Accelerate with GPUs
Mixed Precision
Block Floating Point 16 (BFP16)
BF16 Quantization
Microscaling (MX)
Microexponents (MX)
Accuracy Improvement Algorithms
Automatic Search for Model Quantization
Automatic Search Pro for Model Quantization
Latency and Memory profiling
Using ONNX Model Inference and Saving Input Data in NPY Format
Optional Utilities
Tools

Tutorials

AMD Quark Tutorial: PyTorch Quickstart
Quantizing a Diffusion Model using Quark
LLM Model Depth-Wise Pruning (beta)
Quantizing a Large Language Model with Quark
FP8 Quantization with Per-Channel Static Weights and Per-Token Dynamic Activations
YOLO-X Tiny Quant example
Quark ONNX Quantization Tutorial For AdaQuant
Quark ONNX Quantization Tutorial For AdaRound
Quark ONNX Quantization Tutorial For Block Floating Point (BFP)
Quark ONNX Quantization Tutorial For Cross Layer Equalization (CLE)
Quark ONNX Quantization Tutorial For GPTQ
Quark ONNX Quantization Tutorial For Layerwise Percentile
Quark ONNX Quantization Tutorial For Mixed Precision
Quark ONNX Quantization Tutorial For Image Classification
Quark ONNX Quantization Tutorial For Smooth Quant
Quark ONNX Quantization Tutorial For Auto Search
Quark ONNX Quantization Tutorial For Image Classification
Quark ONNX Quantization Tutorial For AdaQuant
Quark ONNX Quantization Tutorial For Image Classification
Quark ONNX Quantization Tutorial For Auto Search
Quark ONNX Quantization Tutorial For Auto Search
Quark ONNX Quantization Tutorial For Auto Search
Quark ONNX Quantization Tutorial For Resnet50
Quark ONNX Quantization Tutorial For YOLOv8
Quantizing ONNX Models with Custom Operators Using Quark

Third-party contributions

Introduction and guidelines

Experimental Features

Quark CLI
- ONNX Adapter

APIs

PyTorch APIs
ONNX APIs
- Quantization
- Quantizer Configuration

Troubleshooting and Support

PyTorch Troubleshooting
ONNX Troubleshooting

AMD Quark release history
Quark license

Language Model Optimization

Language Model Optimization

Language Model Optimization#

LLM Pruning
Language Model Post Training Quantization (PTQ) Using Quark
Language Model QAT Using Quark and Trainer
Language Model Evaluations in Quark
Rotation pre-processing optimization

previous

Debugging quantization degradation in AMD Quark

next

LLM Pruning

Last updated on Jan 16, 2026.

Terms and Conditions
Quark Licenses and Disclaimers
Privacy
Trademarks
Supply Chain Transparency
Fair and Open Competition
UK Tax Strategy
Cookie Policy
Cookie Settings

© 2025 Advanced Micro Devices, Inc