NVIDIA DGX Spark In-Depth Review: A New Standard for Local AI Inference

Re:NVIDIA DGX Spark In-Depth Review: A New Standard for Loca... by yvbbrjdr on Tuesday October 14, 2025 @02:03AM (#45576752)

I see! Do you know what's causing the slowdown for ollama? They should be using the same backend..

[ Parent | on HN ]

Re:NVIDIA DGX Spark In-Depth Review: A New Standard for Loca... by alecco on Tuesday October 14, 2025 @05:01AM (#45577779)

Dude, ggerganov is the creator of llama.cpp. Kind of a legend. And of course he is right, you should've used llama.cpp.

Or you can just ask the ollama people about the ollama problems. Ollama is (or was) just a Go wrapper around llama.cpp.

[ Parent | on HN ]

Re:NVIDIA DGX Spark In-Depth Review: A New Standard for Loca... by ilc on Tuesday October 14, 2025 @07:34AM (#45578770)

Was. They've been diverging.

[ Parent | on HN ]