AI models
Oryx 34B
Parameters
34B
Published
Sep 19, 2024
Oryx 34B is an AI model developed by Tsinghua University, Tencent and Nanyang Technological University (China and Singapore), first published in September 2024. It works in the multimodal, vision, 3d modeling and 2 more domain, on tasks such as visual question answering, video compression, image captioning and 2 more.
Epoch AI has no training-compute estimate for this model. The model has 34,000,000,000 parameters. Training ran on 64 NVIDIA A800 SXM.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Yi-1.5-34B. The reference paper has 161 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Tsinghua University, Tencent, Nanyang Technological University
- Country of organization
- China, Singapore
- Domain
- Multimodal, Vision, 3D modeling, Video, Language
- Task
- Visual question answering, Video compression, Image captioning, Video description, Language modeling/generation
- Parameters
- 34,000,000,000
- Training hardware
- NVIDIA A800 SXM
- Chips used
- 64
- Training power draw
- 50.4 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- Yi-1.5-34B
- Citations
- 161
- Epoch confidence
- Confident
More from Tsinghua University,Tencent,Nanyang Technological University
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