AI models
LLaVA-NeXT-32B-Qwen
Parameters
32B
Published
Jul 16, 2024
LLaVA-NeXT-32B-Qwen is an AI model developed by LMMs-Lab, first published in July 2024. It works in the multimodal and language domain, on tasks such as chat, language modeling/generation, visual question answering and image captioning.
Epoch AI has no training-compute estimate for this model. The model has 32,000,000,000 parameters. Training ran on 64 NVIDIA A100 SXM4 80 GB for about 35 hours.
Access: Open weights (restricted use). Its weights are openly available. It is built on top of Qwen1.5-32B. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- LMMs-Lab
- Domain
- Multimodal, Language
- Task
- Chat, Language modeling/generation, Visual question answering, Image captioning
- Compute estimation method
- Hardware
- Parameters
- 32,000,000,000
- Training hardware
- NVIDIA A100 SXM4 80 GB
- Chips used
- 64
- Training time
- 35 h
- Training power draw
- 50.5 kW
- Model accessibility
- Open weights (restricted use)
- Open weights
- Yes
- Base model
- Qwen1.5-32B
- 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