AI models
LLaVA 1.5
Training compute
7.8×10²² FLOP
Parameters
13B
Published
Nov 5, 2023
LLaVA 1.5 is an AI model developed by University of Wisconsin Madison and Microsoft Research (United States), first published in November 2023. It works in the multimodal, language and vision domain, on tasks such as chat, question answering and visual question answering.
Training it took an estimated 7.8×10²² FLOP of compute (estimation method: hardware). The model has 13,000,000,000 parameters. Training ran on 8 NVIDIA A100 for about 24 hours.
Access: Open weights (restricted use). Its weights are openly available. It is built on top of Vicuna-13B v0. The reference paper has 5,077 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Wisconsin Madison, Microsoft Research
- Country of organization
- United States
- Domain
- Multimodal, Language, Vision
- Task
- Chat, Question answering, Visual question answering
- Training compute
- 7.8×10²² FLOP
- Compute estimation method
- Hardware
- Parameters
- 13,000,000,000
- Training hardware
- NVIDIA A100
- Chips used
- 8
- Training time
- 24 h
- Chip-hours
- 192
- Training power draw
- 6.3 kW
- Numerical format
- BF16
- Model accessibility
- Open weights (restricted use)
- Open weights
- Yes
- Base model
- Vicuna-13B v0
- Citations
- 5,077
- 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