Collections · For builders
Run AI on Your Own Machine
The pieces for running language and image models locally instead of through a hosted API.
Last reviewed Oct 2, 2026. Open in the explorer to search and filter within it.
- 1
LLM inference in C/C++
The inference engine many local tools are built on; runs models on CPUs and consumer GPUs.
- 2
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Download and run models with one command, behind a local API.
- 3
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A chat interface for local models, with Ollama and OpenAI-compatible backends.
- 4
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Node-based workflows for image and video generation models.
- 5
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
A self-hosted, OpenAI-compatible API in front of local models.
- 6
A high-throughput and memory-efficient inference and serving engine for LLMs
High-throughput model serving, for when one machine has to serve many requests.