Verified65% confidenceEventExact time
In early 2023, Georgi Gerganov completed the initial implementation of llama.cpp in just a few days, porting Meta's LLaMA model to a pure C/C++ environment and running CPU inference on a MacBook.
3
Sources
65%
Confidence
Long-term
Relevance
7/8/2026
First Seen
Sources
Related Claims
UnverifiedGeorgi Gerganov 于 2023 年初发布的 llama.cpp 首次证明仅凭 CPU 就能在普通笔记本上运行大语言模型75% similarUnverifiedllama.cpp was released by Bulgarian engineer Georgi Gerganov in March 2023, originally reproducing the inference logic of Meta's LLaMA model in a few hundred lines of C/C++.73% similarVerifiedllama.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69% 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69% similarUnverifiedllama.cpp 最初目标是让 Meta 的 LLaMA 模型能在普通消费级硬件上运行，尤其是 Apple Silicon 的 MacBook66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/298493API
curl https://kongchang.com/api/v1/knowledge/claims/298493MCP
get_claim(id=298493)