Timer-S1
Model directorybytedance-research/Timer-S18.3B total / 0.75B active params | Apache-2.0 | Upstream checkpoint
Timer-S1 is ByteDance's billion-scale sparse MoE time-series foundation model and the high-capacity entry in the Timer line. With 8.3B total parameters but only 0.75B active per token, it is positioned as a top-tier zero-shot forecaster, reaching state-of-the-art MASE and CRPS on the GIFT-Eval leaderboard.
Architecturally it is a decoder-only sparse Mixture-of-Experts transformer built around Serial-Token Prediction (STP) and an 11.5K-token context window, and it natively emits 9-quantile probabilistic forecasts rather than a bare point estimate. It is pretrained on TimeBench, a curated corpus of one trillion time points spanning diverse domains, with data augmentation applied to mitigate predictive bias, and it is released under Apache-2.0.
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
Timer
Type
time series foundation model
Pretrained time-series model for zero-shot or few-shot forecasting workloads.
Resources
Training Data
TimeBench, a curated corpus with one trillion time points spanning diverse domains, with data augmentation to mitigate predictive bias.
Recommended For
- • Zero-shot univariate forecasting with causal autoregressive generation
- • Long-horizon prediction across heterogeneous time-series domains
Strengths
- • TimeAttention unifies variable-length and multi-resolution inputs
- • Strong zero-shot performance from 260B-point pretraining
Limitations
- • Smaller model family with fewer checkpoint size options than Chronos or Moirai
- • Causal-only architecture limits suitability for bidirectional tasks like imputation
- • Hosted Timer serving works best once you have at least one full 96-point patch of history; very short series are a poor fit
- • Evaluate repeated seasonal patterns against specialist zero-shot baselines on your own data
Not Ideal For
- • Histories shorter than one full 96-point patch
- • Users who need strong seasonal continuation on very small repeated-pattern probes without tuning
Capabilities
Tags
Specifications
- Parameters
- 8.3B total / 0.75B active
- Architecture
- decoder-only sparse MoE transformer with Serial-Token Prediction (STP)
- 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
- Apache-2.0