phi-3.5-mini

Training compute

3.7×10²² FLOP

Parameters

3.8B

Published

Apr 23, 2024

phi-3.5-mini is an AI model developed by Microsoft (United States), first published in April 2024. It works in the language domain, on tasks such as language modeling/generation, question answering and translation.

Training it took an estimated 3.7×10²² FLOP of compute (estimation method: hardware,operation counting). The model has 3,800,000,000 parameters. Training ran on 512 NVIDIA H100 SXM5 80GB for about 240 hours.

Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Microsoft
Country of organization: United States
Domain: Language
Task: Language modeling/generation, Question answering, Translation
Training compute: 3.7×10²² FLOP
Compute estimation method: Hardware, Operation counting
Parameters: 3,800,000,000
Training hardware: NVIDIA H100 SXM5 80GB
Chips used: 512
Training time: 240 h
Training power draw: 708.4 kW
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Epoch confidence: Confident