AI models
ColPali
Parameters
3B
Published
Jul 5, 2024
ColPali is an AI model developed by Illuin Technology, Equall.ai, University Paris-Saclay and ETH Zurich (France, United States and Switzerland), first published in July 2024. It works in the vision domain, on tasks such as character recognition (ocr).
Epoch AI has no training-compute estimate for this model. The model has 3,000,000,000 parameters. Training ran on 8 AMD Radeon Instinct MI250X.
Access: Open weights (restricted use). Its weights are openly available. It is built on top of PaliGemma. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Illuin Technology, Equall.ai, University Paris-Saclay, ETH Zurich
- Country of organization
- France, United States, Switzerland
- Domain
- Vision
- Task
- Character recognition (OCR)
- Compute estimation method
- Hardware
- Parameters
- 3,000,000,000
- Training hardware
- AMD Radeon Instinct MI250X
- Chips used
- 8
- Chip-hours
- 40
- Training power draw
- 7.9 kW
- Numerical format
- BF16
- Model accessibility
- Open weights (restricted use)
- Open weights
- Yes
- Base model
- PaliGemma
- 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