Both Open d1 models run across NVIDIA DGX, RTX, and Jetson, with day-one llama.cpp support to run anywhere.
Original titleBoth Open d1 models run across NVIDIA DGX, RTX, and Jetson, with day-one llama.cpp support to run anywhere.
AISummary
d1-3B single-question latency, measured one request at a time: > NVIDIA RTX 4090: 8 ms > Jetson AGX Thor: 16 ms > Jetson AGX Orin 64 GB: 26 ms > Jetson Orin Nano: 50 ms 4/
Source: Liquid AI · x.com