OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Local & Self-hosted AI

Geniex

GenieX is an on-device inference runtime for running large language and vision-language models on Qualcomm Snapdragon devices through available NPU, GPU or CPU hardware.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Geniex — OpenViST project profile in Local & Self-hosted AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use GenieX when an application needs local LLM or VLM inference on Qualcomm Snapdragon hardware and the developer wants a CLI, programming-language interface, Docker workflow or OpenAI-compatible local server.

Who it is for

  • Developers building local LLM applications for Qualcomm Snapdragon devices.
  • Developers integrating vision-language inference into on-device applications.
  • Teams using Python, Android Kotlin/Java, a CLI, Docker or an OpenAI-compatible local server as their integration path.

Documented uses

  • Run a GGUF language or vision-language model locally through llama.cpp.
  • Run a pre-compiled Qualcomm AI Hub model bundle through Qualcomm AI Engine Direct on the NPU.
  • Integrate local text generation into a Python workflow.
  • Expose a locally running model through an OpenAI-compatible server.
  • Add model inference to an Android application using the documented Android SDK interface.
Before you choose

Requirements & limits

The repository labels GenieX a developer preview and identifies a BSD-3-Clause license. Its documented target platforms are Windows ARM64, Android and Linux ARM64 on Qualcomm devices.

  • Hardware scope is Qualcomm Snapdragon; the README lists Windows ARM64, Android and Linux ARM64 device paths.
  • GGUF examples use llama.cpp and can run on NPU, GPU or CPU; pre-compiled Qualcomm AI Hub bundles use Qualcomm AI Engine Direct on the NPU.
  • The interface options include CLI, Python, Android Kotlin/Java, Docker and an OpenAI-compatible server.
  • The repository describes GenieX as the community version of Qualcomm GENIE and marks it as a developer preview.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install GenieX CLI on Linux ARM64

Install the GenieX CLI on a Linux ARM64 system before using its model-inference commands.

Before you start

  • A Linux ARM64 Qualcomm device.
  • A terminal with access to the documented installer URL.

Steps

  1. Run the Linux ARM64 installer command from the GenieX README: curl -fsSL https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-geniex/install.sh | sh.

  2. Open a new terminal after installation, as the README directs.

Expected outcome

The CLI is installed and ready for the documented inference workflow.

Guide limitations

  • This guide covers installation only; the README's inference examples are separate steps.
  • The documented platform path is Linux ARM64 on Qualcomm hardware.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Model inference and serving

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
GeniexRun a GGUF language or vision-language model locally through llama.cpp.Self-hostedThe repository labels GenieX a developer preview and identifies a BSD-3-Clause license. Its documented target platforms are Windows ARM64, Android and Linux ARM64 on Qualcomm devices.
PmetalRun inference with a selected model and prompt, including a LoRA adapter.macOS, Self-hostedThe project documents prebuilt binaries, a crates.io package and source builds. Building the optional desktop GUI requires Bun in addition to its separate build command.
LlmfitIdentify models and quantizations that match available CPU, RAM, GPU and VRAM.CLI, Desktop, Linux, macOSThe repository is public and MIT-licensed. Documented installation routes include Scoop, Homebrew, MacPorts, uv, pip and pre-built binaries for Windows, macOS and Linux.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
qualcomm/GenieX · Official homepage title · retained in its source language
How we review sourcesSuggest a correction