RUNTIME / MEDIUM
llama.cpp
GGUF models, CPU/GPU offload, embedded and unusual hardware
1차 출처DifficultyMediumSetup profile
Platforms5cpu · apple · nvidia · amd · intel
APIOpenAI-compatible server:8080
01 / INSTALL & RUN
- 1Install
brew install llama.cpp # or use upstream binaries - 2Start a model
llama-server -hf google/gemma-3-1b-it --port 8080 - 3Connect your app
OpenAI-compatible server · :8080. Keep the service bound to localhost unless you add authentication and network controls.
주의
New architectures may require a recent build. Backend availability does not imply equal performance.
02 / COMPATIBLE MODELS