Is this using only llama.cpp as inference engine? How is this days support there... | Hacker News

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

pzo on July 11, 2025 | parent | context | favorite | on: Show HN: Cactus – Ollama for Smartphones

Is this using only llama.cpp as inference engine? How is this days support there on NPU and GPU? Not sure if LLM can run on NPU but many models like STT and TTS and vision often can run much faster on Apple NPU

liuliu on July 11, 2025 [–]

You don't need to guess: https://github.com/cactus-compute/cactus/tree/main/cpp

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact