Alternatives to NexaSDK for Mobile

On-device GenAI SDK for Qualcomm Snapdragon — now folded into Qualcomm AI Hub.

Run 15+ offline AI models on your phone for private, on-device chat, image, music and code generation.

Run any GGUF AI model locally on Android with zero network permissions

LFM2.5 is Liquid AI's open-weight foundation model family for on-device AI — native text, vision, and audio inference on CPU, GPU, or NPU.

Supertonic delivers free on-device text-to-speech you download and run locally via ONNX Runtime, with no per-character bill.

Typeahead is on-device AI autocomplete for Mac that finishes your sentences in any app with one Tab.

picoLLM is Picovoice's on-device LLM inference engine for running quantized language models locally on phones, embedded Linux, web, and microcontrollers.

Iris Android runs GGUF language models offline on your phone using llama.cpp — no server, no account, no data leaving the handset.

Cotypist predicts your next words inline in every Mac app — on-device text prediction that never sends your writing to the cloud.

QVAC SDK puts on-device AI in one JavaScript or Python API — text, vision and audio with no cloud and no API keys

Run local HuggingFace models or route prompts to Claude, GPT and Gemini with your own API keys

BitNet (bitnet.cpp) runs 1-bit and ternary BitNet b1.58 LLMs on CPU with lossless 1.58-bit inference — no GPU needed.

Ollama runs open-weight LLMs locally or in the cloud with one command and an OpenAI-compatible API.

Free local RAG chatbot from NVIDIA that answers questions over your own files on an RTX Windows PC

LM Studio runs open-source LLMs locally with Bionic, an agent for coding, documents and automation.

Free, open-source desktop app for running and fine-tuning RWKV RNN language models locally with effectively unbounded context.

Free open-source local AI server that runs LLMs, image, music, video, and 3D generation on your own Apple Silicon Mac.

Run Llama 3.1 405B and other huge language models at home over a BitTorrent-style decentralized inference network.

Free, MIT-licensed local LLM inference for Apple Silicon Macs, with SSD-backed prefix caching and native OpenAI and Anthropic APIs.

Open-source, local-first desktop AI client that connects to multiple model providers and keeps your data on your machine.

Atomic Chat runs 1,000+ local LLMs offline on your own hardware — free, open-source, no account, no rate limits.

Enclave runs open-source AI models locally on your iPhone and Mac for private, fully offline AI chats.

Mesh LLM splits giant open-weight models across your own GPUs and serves them as one local OpenAI-compatible endpoint on localhost:9337.

PrivateGPT is the open-source on-premise RAG framework for local document Q&A — 57k GitHub stars, zero cloud calls.

Run Afterglow locally to turn exported QQ and WeChat chat logs into a searchable AI friend that answers in a real person's voice

Open-source Kubernetes operator for self-hosted LLM, embedding, reranking, and speech-to-text inference with an OpenAI-compatible API.

A free desktop app that runs the Mistral 7B model on your own machine, so you can chat with spreadsheets and PDFs without uploading them anywhere.

CoreAI-Model-Zoo: downloadable .aimodel bundles and rerunnable conversion recipes for Apple's Core AI on iPhone and Mac.

LocalAI is an MIT-licensed local AI runtime that serves text, voice, vision, image and agent workloads behind an OpenAI-compatible API.

A free, open-source desktop chat client that runs your own OpenAI, Azure OpenAI, Google, and Replicate API keys from one window.