MOMENT-Base
Model directoryAutonLab/MOMENT-1-base~125M params | MIT | Upstream checkpoint
MOMENT-Base is the mid-size checkpoint in AutonLab's MOMENT family, providing a balance between the lightweight Small variant and the higher-capacity Large model. It is the natural default when MOMENT-Small leaves quality on the table but MOMENT-Large is more backbone than a task needs.
It shares the same architecture and multi-task transfer capabilities as the rest of the family: a patch-based encoder-only transformer trained with masked time-series modeling, producing representations that transfer across forecasting, classification, anomaly detection, imputation, and embedding extraction. It is trained on Timeseries-PILE, built from public forecasting, classification, and anomaly-detection corpora including Informer datasets, Monash, UCR/UEA, and TSB-UAD. The upstream momentfm package warns that only the reconstruction head is pretrained and that forecasting heads must be fine-tuned, so zero-shot forecast quality should be treated as secondary to backbone reuse.
Where to run this model
Compute availability, hardware requirements, and pricing depend on the execution provider.
Get model weights, deployment instructions, and current provider listings.
Hugging Face provider mappings checked 2026-10-06. No Inference Provider mapping was listed for this checkpoint.
Model Classification
Family
MOMENT-1
Type
time series foundation model
Pretrained time-series model for zero-shot or few-shot forecasting workloads.
Resources
Training Data
Timeseries-PILE, built from public forecasting, classification, and anomaly-detection corpora including Informer datasets, Monash, UCR/UEA, and TSB-UAD.
Recommended For
- • Shared backbones across forecasting, anomaly detection, classification, and imputation
- • Teams that want one general-purpose time-series representation model
Strengths
- • Multi-task time-series understanding
- • Useful when the same deployment needs to cover several downstream tasks
Limitations
- • Not optimized purely around one forecasting leaderboard objective
- • May be heavier than needed if you only need straightforward zero-shot forecasting
- • The upstream momentfm package warns that only the reconstruction head is pretrained and that forecasting heads must be fine-tuned
- • Hosted forecasting quality can lag specialist zero-shot forecasters because MOMENT is primarily framed as a transferable representation backbone
- • Zero-shot forecasting tends to be trend-blind — predictions may flatten regardless of clear trends in the input
Not Ideal For
- • Choosing a default forecast-only model when you mostly care about zero-shot continuation quality
- • Short benchmark-style trend extrapolation where specialist forecasting families are stronger
Capabilities
Tags
Specifications
- Parameters
- ~125M
- Architecture
- patch-based encoder-only transformer trained with masked time-series modeling
- Context length
- n/a
- Max context
- n/a
- Minimum history
- n/a
- Recommended history
- n/a
- Input step
- n/a
- Required target series
- 1
- Temperature
- Ignored
- Top P
- Ignored
- Max output
- n/a
- License
- MIT