Verified90% confidenceFactTime unknown
llama.cpp是由Georgi Gerganov开发的纯C/C++推理引擎，支持在纯CPU环境下运行大模型
15
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
Verifiedllama.cpp是一个纯C/C++实现的推理框架，支持CPU推理和极低比特量化（如4-bit、2-bit），可在笔记本电脑甚至树莓派上运行LLM79% similarUnverifiedllama.cpp is a pure C/C++ inference engine developed by Georgi Gerganov, supporting multiple quantization formats including Q4_0, Q4_K_M, and Q5_K_M.79% similarUnverifiedllama.cpp 用纯 C/C++ 重新实现了 LLaMA 模型的推理逻辑，无需 GPU 仅凭 CPU 就能运行大语言模型79% similarUnverifiedllama.cpp 是由 Georgi Gerganov 开发的 C++ 推理引擎，通过量化技术将模型权重从32位浮点数压缩为4位或8位整数78% similarUnverifiedllama.cpp 由 Georgi Gerganov 开发，实现了纯 CPU 推理；MLC LLM 实现了在 iPhone 上运行 7B 模型的能力78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/33661API
curl https://kongchang.com/api/v1/knowledge/claims/33661MCP
get_claim(id=33661)