AI models
MULAN
Training compute
5.2×10²⁰ FLOP
Parameters
35M
Published
Jun 2, 2024
MULAN is an AI model developed by AIRI Artificial Intelligence Research Institute, Skolkovo Institute of Science and Technology, Belozersky Institute of Physio-Chemical Biology and Ligand Pro (Russia), first published in June 2024. It works in the biology domain, on tasks such as protein or nucleotide language model (plm/nlm).
Training it took an estimated 5.2×10²⁰ FLOP of compute (estimation method: hardware). The model has 35,000,000 parameters. Training ran on 1 NVIDIA H100 SXM5 80GB.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of ESM2-35M. The reference paper has 7 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- AIRI Artificial Intelligence Research Institute, Skolkovo Institute of Science and Technology, Belozersky Institute of Physio-Chemical Biology, Ligand Pro
- Country of organization
- Russia
- Domain
- Biology
- Task
- Protein or nucleotide language model (pLM/nLM)
- Training compute
- 5.2×10²⁰ FLOP
- Compute estimation method
- Hardware
- Parameters
- 35,000,000
- Training hardware
- NVIDIA H100 SXM5 80GB
- Chips used
- 1
- Training power draw
- 760 W
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- ESM2-35M
- Citations
- 7
- 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