AI models
SmolLM-1.7B
Training compute
10²² FLOP
Parameters
1.7B
Published
Jul 16, 2024
SmolLM-1.7B is an AI model, first published in July 2024. It works in the language domain, on tasks such as chat, question answering and language modeling/generation.
Training it took an estimated 10²² FLOP of compute (estimation method: operation counting). The model has 1,710,000,000 parameters. Training ran on 64 NVIDIA H100 PCIe.
Access: Open weights (unrestricted). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Domain
- Language
- Task
- Chat, Question answering, Language modeling/generation
- Training compute
- 10²² FLOP
- Compute estimation method
- Operation counting
- Parameters
- 1,710,000,000
- Training hardware
- NVIDIA H100 PCIe
- Chips used
- 64
- Training power draw
- 44.2 kW
- Numerical format
- BF16
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Epoch confidence
- Confident
More ai models
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