Qualcomm AI Hub Models
Community GGUF Models
Developer Preview
GenieX
Run Any Gen AI Model On Device
NPU
GPU
CPU
What is GenieX
An on-device Gen AI inference runtime built for Qualcomm platforms.
Run frontier language and vision-language models locally on Hexagon NPU, Adreno GPU, or CPU with a few lines of code, via the path best for your deployment:
QAIRT plugin
Optimal NPU Performance
Run models optimized for NPU via the Qualcomm® AI Runtime (QAIRT).
GenieX
CLI
GenieX
Python API
GenieX
Java API
GenieX
Docker
GenieX Server
(OpenAI / OpenClaw)
GenieX SDK
GenieX - llama.cpp Plugin
GenieX - QAIRT Plugin
GGML Runtime
GGML CPU
Kernels
GGML GPU
Kernels
GGML HTP
Kernels
Qualcomm® AI Runtime (QAIRT) SDK
CPU
GPU
NPU
Get Started within 5 Minutes
Easily bring your models from development to production.
