AI models
MamayLM
Training compute
4.4×10²³ FLOP
Parameters
9B
Published
Apr 23, 2025
MamayLM is an AI model developed by INSAIT and ETH Zurich (Bulgaria and Switzerland), first published in April 2025. It works in the language domain, on tasks such as language modeling/generation and language generation.
Training it took an estimated 4.4×10²³ FLOP of compute. The model has 9,000,000,000 parameters. It was trained on roughly 8.1T datapoints.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as likely.
Full record
- Organization
- INSAIT, ETH Zurich
- Country of organization
- Bulgaria, Switzerland
- Domain
- Language
- Task
- Language modeling/generation, Language generation
- Training compute
- 4.4×10²³ FLOP
- Parameters
- 9,000,000,000
- Dataset size
- 8.1T
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Likely
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