Run large language models locally — llama, codellama, mistral, and more. Runs on CPU by default; GPU passthrough is on the roadmap.
Tech stack
LLM Self-hosted GGUF
Back to catalog 
Ollama AI Server
AI 0.0
Run large language models locally — llama, codellama, mistral, and more. Runs on CPU by default; GPU passthrough is on the roadmap.