Awesome local LLM
A curated list of platforms, inference engines, models, tools, and tutorials for running large language models on one's own hardware.
Awesome local LLM is a curated list of platforms, tools, and resources for running large language models locally rather than through a hosted API. It organizes inference platforms, inference engines such as llama.cpp, vLLM, and Ollama, user interfaces, and specific models by category, from general-purpose and coding models to multimodal, image, and audio models.
Beyond running models, it lists tools for agent frameworks, the Model Context Protocol, retrieval-augmented generation, coding agents, computer use, browser automation, memory management, testing and observability, training and fine-tuning, and security and sandboxing, plus hardware guidance, tutorials on prompt and context engineering, and community links. A companion list separately catalogs environments for running coding agents in parallel.
It is a Markdown list released under the MIT license.