Alternatives hub · graph-backed
llama.cpp alternatives
Not a popularity vote. Each is a typed edge from llama.cpp with the reason it exists in Inference & Serving - ranked with live GitHub stats, not marketing.
self-llm
《开源大模型食用指南》
Jupyter Notebookinference-serving
31k
stars
airllm
Repository for running large language models with reduced memory usage on limited GPU hardware.
Jupyter Notebookinference-serving
22k
stars