# Tutorials

Note

To enable or configure logging for the tutorials below, see the [Logging Configuration](https://docs.qualcomm.com/doc/80-87189-2/topic/qairt-logging-utility.html) page.

## Core API Tutorials

This section contains tutorials that showcase how to use the Python API for non-Gen AI use cases.

The tutorials are split into two sections depending on your target platform.

### For Android devices

For android devices, please follow the sections below to learn how to execute and profile models with the Python API:

- [Mobilenet V2 Inference on HTP](https://docs.qualcomm.com/doc/80-87189-2/topic/on_device_inference.html)
- [Profiling Models with QAIRT Visualizer](https://docs.qualcomm.com/doc/80-87189-2/topic/profiling_models_with_visualizer.html)

In certain cases, additional inference performance improvements can be achieved by tuning the model. For more information on how to tune models,
please refer to the following section:

- [Tuning Models](https://docs.qualcomm.com/doc/80-87189-2/topic/tuning_tutorial.html)

### For Windows on Snapdragon devices

For Windows on Snapdragon (WoS) devices, please follow the sections below to learn how to execute with the Python API:

- [Mobilenet V2 Inference on HTP](https://docs.qualcomm.com/doc/80-87189-2/topic/wos_on_device_inference.html)

### For arm-linux devices

arm-linux refers to Linux-aarch64 platforms, which come in two variants:

- **Ubuntu 24.04** (aarch64)
- **QLI** (Qualcomm Linux)

Both require **Python 3.12** to install and run `qairt-dev`. Example devices include
QCS6490, QCS8275, and QCS9075.

Development is now supported directly on arm-linux devices: you can prepare a model
(convert, quantize, and compile) and execute it natively on the device. Alternatively, you
can prepare and drive execution remotely from a host machine. Follow the sections below:

- [ResNet50 Native Inference on arm-linux](https://docs.qualcomm.com/doc/80-87189-2/topic/native_inference.html)
- [Mobilenet V2 Remote Inference on arm-linux](https://docs.qualcomm.com/doc/80-87189-2/topic/remote_inference.html)

## Gen AI API Tutorials

This section contains tutorials that showcase how to use the Python API for Gen AI use cases.

### Android devices

For android devices, please follow the sections below to learn how to perform text generation with the Python API:

- [LLM Inference on HTP](https://docs.qualcomm.com/doc/80-87189-2/topic/genai_builder.html)
- [Vision-Language Model Inference on HTP](https://docs.qualcomm.com/doc/80-87189-2/topic/lmm_builder.html)
- [GGUF Inference on HTP](https://docs.qualcomm.com/doc/80-87189-2/topic/gguf_builder.html)
- [GGUF Calibration for Activation Encodings](https://docs.qualcomm.com/doc/80-87189-2/topic/gguf_calibration.html)
- [Low-Rank Adaptation (LoRA) Tutorial](https://docs.qualcomm.com/doc/80-87189-2/topic/lora_tutorial.html)
- [Speculative Decoding Tutorial](https://docs.qualcomm.com/doc/80-87189-2/topic/speculative_decoding_tutorial.html)

Last Published: Aug 19, 2026

[Previous Topic
Support](https://docs.qualcomm.com/bundle/publicresource/80-87189-2/topics/setup.md) [Next Topic
Mobilenet V2 Inference on HTP](https://docs.qualcomm.com/bundle/publicresource/80-87189-2/topics/on_device_inference.md)