Port of Facebook's LLaMA model in C/C++
Python bindings for llama.cpp
Run Local LLMs on Any Device. Open-source
Personal AI, On Personal Devices
Interface for OuteTTS models
Claude Code, but it runs on your Mac for free
Powerful Android AI agent with tools, automation, and Linux shell
Run a full local LLM stack with one command using Docker
Your Personal AI Assistant; easy to install, deploy on local or coud
Run Bonsai (1-bit) and Ternary-Bonsai language models locally
Structured Outputs
An easy-to-understand framework for LLM samplers
Qwen3 is the large language model series developed by Qwen team
Oobabooga - The definitive Web UI for local AI, with powerful features
Semantic ifs from open models, on a 3090 at home
MiniCPM5: SOTA on-device LLMs, small yet powerful
A proxy server for multiple ollama instances with Key security
Performance-optimized AI inference on your GPUs
GLM-4 series: Open Multilingual Multimodal Chat LMs
First class Sublime Text AI assistant with gpt-5, Opus 4.6, Gemini 3
Towards Human-Sounding Speech
Private AI agents, assistants and search over your own documents
A local-first AI assistant that gets real work done
Implement a small-parameter Chinese large language model from zero