Hacker News new | ask | show | jobs
by lostmsu 155 days ago
You don't have to install the whole CUDA. They have a redistributable.
1 comments
tom_0 154 days ago
Oh, I can't believe I missed that! That makes whisper.cpp and llama.cpp valid options if the user has Nvidia, thanks.
link
lostmsu 153 days ago
Whisper.cpp and llama.cpp also work with Vulkan.
link
tom_0 152 days ago
Yeah, I researched this and I absolutely missed this whole part. To my defense I looked into this in 2023 which is ages ago :) Looks like local models are getting much more mature.
link