notesum.ai

Published at December 4

cs.CL

cs.LG

68T50, 68T07 (Primary) 03B65, 91G15, 91F20 (Secondary)

I.2.7; I.2.1; I.5.1; I.5.2; I.5.4; H.3.3

Released Date: December 4, 2024

Authors: Urjitkumar Patel¹, Fang-Chun Yeh¹, Chinmay Gondhalekar¹, Hari Nalluri¹

Aff.: ¹S&P Global

Model	Inference Time (hr)	Infrastructure	Inference Cost ($)
GPT-4o	1.579	OpenAI API	204.8675
Llama-3.1	0.642	A100 (40 GB)	0.8363
Phi-3	2.254	A100 (40 GB)	2.9362
FANAL	0.013	A100 (40 GB)	0.0017