Table of contents
Nexa SDK
Nexa SDK lets developers run LLMs, multimodal, ASR & TTS models across PC, mobile, automotive, and IoT. Fast, private, and production-ready on NPU, GPU, and CPU.
Nexa SDK is an on-device inference framework that runs any model on any device, across any backend. It runs on CPUs, GPUs, NPUs with backend support for CUDA, Metal, Vulkan, and Qualcomm NPU. It handles multiple input modalities including text ๐, image ๐ผ๏ธ, and audio ๐ง. The SDK includes an OpenAI-compatible API server with support for JSON schema-based function calling and streaming. It supports model formats such as GGUF, MLX, Nexa AI's own .nexa format, enabling efficient quantized inference across diverse platforms.
A startup from Cupertino, the United States.
Pricing:
- Open Source
Platforms:
- Windows
- Mac
- iOS
- Android
- Linux
