AI models
Ferret (13B)
Parameters
13B
Published
Oct 11, 2023
Ferret (13B) is an AI model developed by Columbia University and Apple (United States), first published in October 2023. It works in the multimodal, language and vision domain, on tasks such as object recognition and language modeling.
Epoch AI has no training-compute estimate for this model. The model has 13,000,000,000 parameters. It was trained on roughly 172.6M datapoints. Training ran on 8 NVIDIA A100 for about 120 hours.
Access: Open weights (non-commercial). Its weights are openly available. It is built on top of Vicuna-13B v0. The reference paper has 524 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Columbia University, Apple
- Country of organization
- United States
- Domain
- Multimodal, Language, Vision
- Task
- Object recognition, Language modeling
- Parameters
- 13,000,000,000
- Dataset size
- 172.6M
- Training hardware
- NVIDIA A100
- Chips used
- 8
- Training time
- 120 h
- Chip-hours
- 960
- Training power draw
- 6.4 kW
- Numerical format
- BF16
- Model accessibility
- Open weights (non-commercial)
- Open weights
- Yes
- Base model
- Vicuna-13B v0
- Citations
- 524
- 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