# Qualcomm® AI Hub GenieX

## Get Started

- [What is GenieX](https://geniex.aihub.qualcomm.com/en/get-started/what-is-geniex.md): On-device AI inference runtime for Qualcomm Snapdragon — run frontier LLMs and VLMs across CLI, Python, Android, and Docker.
- [Quickstart](https://geniex.aihub.qualcomm.com/en/get-started/quickstart.md): Pick your interface and get to first inference in minutes.
- [Platforms & runtimes](https://geniex.aihub.qualcomm.com/en/get-started/platforms.md): Snapdragon platforms supported by GenieX and which runtime to pick on each.
- [Models](https://geniex.aihub.qualcomm.com/en/models/supported.md): Where to find models, how to run them, and which precisions land on the Snapdragon NPU.

## Run

### Command Line

- [CLI Install](https://geniex.aihub.qualcomm.com/en/run/cli/install.md): Install the GenieX CLI on Windows ARM64, or run it via Docker on Linux ARM64.
- [Quickstart](https://geniex.aihub.qualcomm.com/en/run/cli/quickstart.md): Run your first model from the GenieX CLI.
- [Local server](https://geniex.aihub.qualcomm.com/en/run/cli/local-server.md): Run an OpenAI-compatible HTTP API on localhost backed by Snapdragon NPU/GPU/CPU acceleration.
- [CLI reference](https://geniex.aihub.qualcomm.com/en/run/cli/reference.md): Every GenieX CLI command and flag, with usage examples.

### Python

- [Python Install](https://geniex.aihub.qualcomm.com/en/run/python/install.md): Install the GenieX Python SDK on Windows ARM64 or Linux ARM64.
- [Quickstart](https://geniex.aihub.qualcomm.com/en/run/python/quickstart.md): Run your first model from the GenieX Python SDK on Windows ARM64.
- [API reference](https://geniex.aihub.qualcomm.com/en/run/python/api-reference.md): Complete API documentation for the GenieX Python SDK.

### Linux (Docker)

- [Linux (Docker) Install](https://geniex.aihub.qualcomm.com/en/run/linux/install.md): Run GenieX via Docker on Linux ARM64 with NPU access.

### Android (Kotlin)

- [Android Install](https://geniex.aihub.qualcomm.com/en/run/android/install.md): Add the GenieX Android SDK to your Gradle project from Maven Central.
- [Quickstart](https://geniex.aihub.qualcomm.com/en/run/android/quickstart.md): Run your first model from the GenieX Android SDK in Kotlin.
- [API reference](https://geniex.aihub.qualcomm.com/en/run/android/api-reference.md): GenieX Android SDK — runtime / compute-unit selection, model management, and inference APIs for LLM and VLM.

## Tutorials

- [Benchmarking with geniex-bench](https://geniex.aihub.qualcomm.com/en/tutorials/benchmarking.md): Measure prefill and decode throughput on Windows ARM64 and Linux ARM64 with geniex-bench.
- [Speculative decoding with MTP](https://geniex.aihub.qualcomm.com/en/tutorials/speculative-decoding-mtp.md): Speed up decoding with a Multi-Token Prediction draft model, in the GenieX CLI and the local server.
- [Audio input](https://geniex.aihub.qualcomm.com/en/tutorials/audio-input.md): Transcribe and reason over audio on-device with an audio-capable VLM, in the GenieX CLI, local server, and Python SDK.

## Resources

- [FAQ](https://geniex.aihub.qualcomm.com/en/resources/faq.md): Common questions about GenieX, its runtimes, and supported chipsets.
- [Troubleshooting](https://geniex.aihub.qualcomm.com/en/resources/troubleshooting.md): Common errors and how to fix them.

## Optional

- [GitHub](https://github.com/qualcomm/GenieX)
- [Website](https://aihub.qualcomm.com/)
- [Slack](https://aihub.qualcomm.com/community/slack)

> The links below point to documentation indexes. Follow each `/_llms/` index recursively until you reach documentation pages.

## Indexes

- [Chinese (18 pages)](https://geniex.aihub.qualcomm.com/_llms/cn.md): Documentation for Chinese.