AI models
Marin 8B
Training compute
6.1×10²³ FLOP
Parameters
8B
Published
May 19, 2025
Marin 8B is an AI model developed by Marin (United States), first published in May 2025. It works in the language domain, on tasks such as language modeling/generation, question answering, code generation and quantitative reasoning.
Training it took an estimated 6.1×10²³ FLOP of compute (estimation method: operation counting). The model has 8,000,000,000 parameters. Training ran on Google TPU v5e,Google TPU v4.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Marin
- Country of organization
- United States
- Domain
- Language
- Task
- Language modeling/generation, Question answering, Code generation, Quantitative reasoning
- Training compute
- 6.1×10²³ FLOP
- Compute estimation method
- Operation counting
- Parameters
- 8,000,000,000
- Training hardware
- Google TPU v5e, Google TPU v4
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- 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