AI models
NatureLM-audio
Training compute
1.4×10²¹ FLOP
Parameters
665M
Published
Nov 11, 2024
NatureLM-audio is an AI model developed by Earth Species Project (United States), first published in November 2024. It works in the audio domain, on tasks such as audio classification.
Training it took an estimated 1.4×10²¹ FLOP of compute (estimation method: hardware). The model has 665,000,000 parameters. Training ran on 8 NVIDIA H100 PCIe for about 216 hours.
Access: Open weights (non-commercial). Its weights are openly available. It is built on top of Llama 3.1-8B. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Earth Species Project
- Country of organization
- United States
- Domain
- Audio
- Task
- Audio classification
- Training compute
- 1.4×10²¹ FLOP
- Compute estimation method
- Hardware
- Parameters
- 665,000,000
- Training hardware
- NVIDIA H100 PCIe
- Chips used
- 8
- Training time
- 216 h
- Training power draw
- 5.5 kW
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Base model
- Llama 3.1-8B
- Epoch confidence
- Confident
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models