Alternatives to OnnxStream

LLM Hub runs 15+ AI models fully offline on Android and iOS for private on-device chat, image, video and code generation.

Stability Matrix installs and manages local AI image and video web UIs like ComfyUI from one shared model library

An MIT-licensed, self-hosted AI runtime that serves text, voice, vision, image, video, 3D and agent workloads behind an OpenAI-compatible API.

Run LLMs, speech-to-text, and image generation fully offline on your device via a Kotlin Multiplatform library, an app, and an IDE plugin.

Guaardvark is a free MIT-licensed self-hosted AI studio for local agents, video generation, voice and RAG on your own GPU.

Run open AI models locally with one command, with per-token Ollama Cloud models when local hardware runs out of headroom.

LFM2.5 open-weight models run on-device LLM inference with text, vision, and speech on CPUs, NPUs, and Apple Silicon.

Microsoft's open-source C++ inference framework that runs 1-bit and ternary BitNet b1.58 models locally on CPUs, plus an official GPU kernel.

On-device LLM inference for Apple Silicon: uzu runtime, architecture-co-designed quantization, and models tuned for sub-200ms interactivity.

Atomic Chat runs 1,000+ open models fully offline on your Mac, PC, Linux box or phone, with no account and no message caps.

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.

Enclave runs open-source AI models locally on iPhone and Mac for private offline AI chat, voice, and document Q&A.

AI research lab building tiny sub-1 MB models that run on microcontrollers and edge devices.

Apple Silicon ML platform for training, serving, quantizing, and merging local models on M1–M5 Macs.

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

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

Run local HuggingFace models or route prompts to Claude, GPT and Gemini with your own keys in this free, open-source AI desktop client

AI Playground runs one prompt across up to 3 AI models side by side, with your own API keys and data kept local.

Free .aimodel bundles plus rerunnable conversion recipes for Apple's Core AI runtime on iOS 27 and macOS 27.

Open-source JavaScript library that runs small LLMs like Llama 3.2 1B Instruct inside the browser via WebAssembly and WebGPU.

Free Podman Desktop extension for running open source LLMs locally, with recipes, a model catalog and OpenAI-compatible endpoints.

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

Open-source local AI workspace to run and train text, image, video and audio models on your own hardware

Open WebUI is the self-hosted AI interface for running Ollama, OpenAI, or Anthropic models on your own hardware.

Run open LLMs locally with LM Studio, then let the Bionic agent loose on documents, code and automations.

QVAC SDK: one open-source API for on-device AI across text, vision and audio, with no cloud

picoLLM runs quantized LLMs fully on-device — local inference for phones, embedded Linux, and microcontrollers with no cloud calls.

Offline AI chat on iPhone, iPad, and Mac that runs open-source LLMs on-device via Core ML — no cloud, no data collection.

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

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