Snapdragon Python Packages

termux-diffusion

AmfyUI (ComfyUI Mobile DAG Studio) & Z-Image Turbo (6.0B DiT) On-Device Diffusion Runtime for Android Termux

geniex

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

wattop

btop-style terminal power monitor: power in/out, volts and amps, per-rail SoC power (Windows ARM64 + Linux)

geniex-llama-cpp

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

geniex-qairt

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

quantcost

pip install quantcost — measure what quantization actually costs on your own hardware: speed, size, memory and perplexity for fp32/int8/int4. No PyTorch, no GPU. Submit your machine to the leaderboard.

nexaai-metal

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

nexai

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

nexaai-gpu

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code