l
llama.cpp✓
Local
Georgi Gerganov
Port of Facebook's LLaMA model in C/C++. The foundational project that enables running LLMs on consumer hardware (Mac, Windows, Linux, Android) with high performance.
Free Limits
Hardware dependent性能
Community Votes
283
■ Available Models
Any GGUF Model
■ Tags
CoreActionPerformanceC++