OpenDiLoCo 1.1B

Training compute

6.1×10²⁰ FLOP

Parameters

1.1B

Published

Jul 10, 2024

OpenDiLoCo 1.1B is an AI model developed by Prime Intellect (United States), first published in July 2024. It works in the language domain, on tasks such as language modeling/generation and question answering.

Training it took an estimated 6.1×10²⁰ FLOP of compute (estimation method: operation counting). The model has 1,100,000,000 parameters. Training ran on 32 NVIDIA H100 SXM5 80GB.

Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Prime Intellect
Country of organization: United States
Domain: Language
Task: Language modeling/generation, Question answering
Training compute: 6.1×10²⁰ FLOP
Compute estimation method: Operation counting
Parameters: 1,100,000,000
Training hardware: NVIDIA H100 SXM5 80GB
Chips used: 32
Training power draw: 44.2 kW
Model accessibility: Unreleased
Open weights: No
Epoch confidence: Confident