AI models
Zephyr 141B-A39B
Parameters
141B
Published
Apr 10, 2024
Zephyr 141B-A39B is an AI model developed by Hugging Face, Korea Advanced Institute of Science and Technology (KAIST) and Argilla (United States, South Korea and Spain), first published in April 2024. It works in the language domain, on tasks such as language modeling/generation and question answering.
Epoch AI has no training-compute estimate for this model. The model has 141,000,000,000 parameters. Training ran on 32 NVIDIA H100 SXM5 80GB for about 1.3 hours.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Mixtral 8x22B. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Hugging Face, Korea Advanced Institute of Science and Technology (KAIST), Argilla
- Country of organization
- United States, South Korea, Spain
- Domain
- Language
- Task
- Language modeling/generation, Question answering
- Compute estimation method
- Hardware
- Parameters
- 141,000,000,000
- Training hardware
- NVIDIA H100 SXM5 80GB
- Chips used
- 32
- Training time
- 1 h
- Training power draw
- 44.3 kW
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- Mixtral 8x22B
- 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