Yes, Ollama automatically determines the number of layers to offload based on av... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

gavmor on Jan 12, 2025 | parent | context | favorite | on: Phi 4 available on Ollama

Yes, Ollama automatically determines the number of layers to offload based on available VRAM.

Consider applying for YC's Fall 2026 batch! Applications are open till July 27.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact