local LLM desktop app / inference frontend
A desktop app (Python/Gradio, AGPL-3.0) for running local LLMs — chat, vision, tool-calling and file Q&A — with multiple backends and an OpenAI/Anthropic-compatible API server.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose it for a lighter TypeScript/Electron stack with a bundled inference engine, agent mode and remote provider support
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V
choose it if you want a small TypeScript desktop client instead of a Python/Gradio app
A desktop app for running Large Language Models locally.
choose it on Apple Silicon for a no-Python native server with OpenAI/Anthropic endpoints and a bundled MLX app
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
choose it if you want one local GUI that also covers fast LoRA training and MLX alongside GGUF inference
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
choose it when embedding on-device inference through an SDK rather than deploying a full desktop app
Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS, Windows, Android, iOS.
choose it for a Flutter client to local llama.cpp models that also proxies Ollama, OpenAI and Anthropic
Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models remotely.
choose it for a containerised Go engine with no Python and broader modality coverage behind an OpenAI-compatible API
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
choose it to ship a model plus server as one self-contained executable instead of a Python app
Distribute and run LLMs with a single file.
choose it for a single Rust binary using WebGPU, avoiding both Python and llama.cpp
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
an archived, unmaintained Python/Gradio private-chat UI; only worth it for Apache-2.0 licensing if you accept no further fixes
Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
a zero-setup GUI bundling GGUF chat with image generation and speech, not a swappable component
Portable local AI studio for Windows, Linux, and macOS. Zero-setup GUI for Image Generation, GGUF LLMs, Text to Speech & Speech to Text
a phone/Mac app bundling chat, vision, speech and image generation
The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.
These projects were analysed and named textgen among their alternatives. The relationship is not symmetric — how textgen rates them is a separate judgement, made when textgen is analysed in its own right.
calls textgen “Choose for a self-hosted web UI with broad llama.cpp/HF support, vision, tool-calling, and LoRA training instead of a native desktop app.”
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.