Llama.cpp with CUDA Support on Original Jetson Nano (4GB)

Y	Hacker News new \| ask \| show \| jobs

	Llama.cpp with CUDA Support on Original Jetson Nano (4GB) (github.com)
	2 points by Abishek_Muthian 90 days ago

2 comments

Original title: Llama.cpp with CUDA support on a Jetson Nano

Editorialization: Added 'Original' and (4GB) to highlight that this project adds support to the long abandoned Nvidia Jetson Nano.

Nice work, the benchmarks don't look terrible for what it is, especially the prompt processing.