Home Lab AI — Your Spare Machines Are a Cluster

You have machines sitting around your home lab. A mini PC in the closet. A workstation on the desk. Maybe a desktop doing light work. Together, your home lab has more compute than most cloud instances — you just need software that treats them as one home lab system. Works on macOS, Linux, and Windows.

Ollama Herd turns your home lab into a local AI cluster. One home lab endpoint, zero config, four model types.

What your home lab gets

Device 1 (32GB)    ─┐
Device 2 (64GB)     ├──→  Home Lab Router (:11435)  ←──  Your apps / agents
Device 3 (256GB)   ─┘

• Home lab LLM inference — Llama, Qwen, DeepSeek, Phi, Mistral, Gemma
• Home lab image generation — Stable Diffusion 3, Flux, z-image-turbo
• Home lab speech-to-text — Qwen3-ASR transcription
• Home lab embeddings — nomic-embed-text, mxbai-embed for RAG