Apps similar to MNN Chat include Ollama, which is free and open source. Other options are AnythingLLM, LM Studio, PocketPal and Maid (AI). You're spoiled for choice with Large Language Model (LLM) Tools like MNN Chat: we list more than 25 alternatives for Windows, Mac, Android, Linux and self-hosting.
Supports local deployment of Llama 3, Code Llama, and other language models, enabling users to customize and create personalized models. Ideal for AI development, it offers flexibility for offline AI needs and integrates AI writing and chatbot tools in local setups.
United States
Open-source privacy-focused chatbot platform allowing unlimited document uploads, multi-user and single-user modes, AI-powered chat with documents, vector database and LLM compatibility, customizable interface, message history, secure desktop deployment, and full user controls.
United States
Enables running large language models entirely offline on desktop with integrated chat UI, OpenAI-compatible server, HuggingFace downloads, model discovery, support for multiple LLM formats and architectures, local privacy, GPU/CPU operation, and quick setup.
United States
Maid is a cross-platform Flutter app for interfacing with GGUF / llama.cpp models locally, and with Ollama and OpenAI models remotely.
The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.
Bulgaria
EU
Experience the power of RWKV models directly on your device. Completely offline, privacy-first, and efficient. No internet required.
China
Run open decision models locally: pull and serve Laya, decider, NLI and GLiClass behind a TypeSafe-compatible API. Ollama for decision models.
OptiQ is an MLX-native toolkit for running large language models on Apple Silicon. No PyTorch, no CUDA, no cloud.
The Swiss Army Knife of offline AI. Chat, speak, and generate images. Privacy first, zero internet. Download an LLM and use it on your mobile device. No data ever leaves your phone.
India
Drop-In OpenAI replacement, On-device, local-first, Generate text/image/speech/music/etc... Backend Agnostic: (llama.cpp, diffusers, bark.cpp, etc...), Optional Distributed Inference(P2P/Federated).
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar.
South Korea
