10-17-2026, 05:36 AM
I think the bottleneck is somewhere else. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
|
desktop apps around local AI with llama.cpp
|
|
« Next Oldest | Next Newest »
|
| Messages In This Thread |
|
desktop apps around local AI with llama.cpp - by vramstream - 10-17-2026, 04:22 AM
Re: desktop apps around local AI with llama.cpp - by torchshed66 - 10-17-2026, 05:36 AM
Re: desktop apps around local AI with llama.cpp - by mlxgarden - 10-17-2026, 02:26 PM
Re: desktop apps around local AI with llama.cpp - by vectorport - 10-17-2026, 03:33 PM
Re: desktop apps around local AI with llama.cpp - by batchshed - 10-17-2026, 03:48 PM
Re: desktop apps around local AI with llama.cpp - by rocmhouse90 - 10-18-2026, 10:25 PM
Re: desktop apps around local AI with llama.cpp - by mlxgarden - 10-19-2026, 04:09 AM
Re: desktop apps around local AI with llama.cpp - by mlxgarden - 10-18-2026, 12:08 AM
Re: desktop apps around local AI with llama.cpp - by mintstation99 - 10-18-2026, 02:23 AM
Re: desktop apps around local AI with llama.cpp - by modgarden - 10-18-2026, 03:56 AM
Re: desktop apps around local AI with llama.cpp - by audionode8 - 10-18-2026, 06:22 PM
|
Users browsing this thread: 1 Guest(s)