News for hackers. Stuff that matters.

A comment on Run Google Gemma 2 2B 100% Locally. Parent comment

Re:Run Google Gemma 2 2B 100% Locally by mappu on Wednesday July 31, 2024 @07:48PM (#41124761)
ollama is a thin wrapper over llama.cpp, so i'd pose the opposite question - what does ollama give you over using llama.cpp directly?
[ Parent | on HN ]
Re:Run Google Gemma 2 2B 100% Locally by schappim on Wednesday July 31, 2024 @07:53PM (#41124799)
Model management, customisable HTTP APIs, monitoring, security features, "parallel requests" (batch processing), no requirement for HF auth etc...
[ Parent | on HN ]
Re:Run Google Gemma 2 2B 100% Locally by yjftsjthsd-h on Wednesday July 31, 2024 @08:29PM (#41125013)
Ease of use. Rather like arduino or like docker vs chroot/jails/zones, there's nothing wrong with just using the underlying tech, but lowering friction has value.
[ Parent | on HN ]