NexaSDK
Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.
Cost / License
- Free
- Open Source (Apache-2.0)
Platforms
- Windows
- Android
- iPhone
- Mac
- Linux
Features
NexaSDK News & Activities
Recent activities
bugmenot added NexaSDK as alternative to AI Playground
bugmenot added NexaSDK as alternative to FastFlowLM
bugmenot added NexaSDK as alternative to AI00 RWKV Server
bugmenot added NexaSDK as alternative to AI Dev Gallery and LocalAI
bugmenot added NexaSDK as alternative to Lemonade Server, llama.cpp and vllm-playground
bugmenot added NexaSDK as alternative to RWKV Runner and RWKV Chat
bugmenot added NexaSDK as alternative to Nexa Studio
NexaSDK information
Developed by
Nexa AI Licensing
Open Source (Apache-2.0) and Free product.Alternatives
16 alternatives listedSupported Languages
- English
Featured in Lists
Wake up the NPU on your device
What is NexaSDK?
NexaSDK is an easy-to-use developer toolkit for running any AI model locally — across NPUs, GPUs, and CPUs — powered by our NexaML engine, built entirely from scratch for peak performance on every hardware stack. Unlike wrappers that depend on existing runtimes, NexaML is a unified inference engine built at the kernel level. It’s what lets NexaSDK achieve Day-0 support for new model architectures (LLM. VLM, CV, Embedding, Rerank, ASR, TTS). NexaML supports 3 model formats: GGUF, MLX, and Nexa AI's own .nexa format.