TimesFM 3.0
v3.0Model directorygoogle/timesfm-3.0-pytorchtimesfm-non-commercial-license-v1.0 (weights) | Upstream checkpoint
TimesFM 3.0 is Google Research's August 2026 release with native multivariate forecasting and flexible past-only or past-and-future covariates. It extends the TimesFM family beyond the earlier univariate interfaces. Evaluate the exact checkpoint and input contract on your workload rather than transferring results from earlier versions.
The source code is Apache-2.0, but downloaded pretrained weights use timesfm-non-commercial-license-v1.0 and are restricted to non-commercial, non-production use. Authorized Google Cloud services offer a separate commercial and production path under their service terms. Check the upstream license before choosing an execution provider.
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.
- Google Cloud BigQuery ML
managed service · Source checked 2026-10-06
Use the built-in TimesFM service with AI.FORECAST. Commercial service use follows Google Cloud terms; it is distinct from downloading restricted pretrained weights.
- sktime TServe
self-hosted runtime · Family / provider variant · Source checked 2026-10-06
Run a model-serving container on your own hardware or compute account. Select the catalog checkpoint and matching runtime image.
Hugging Face provider mappings checked 2026-10-06. No Inference Provider mapping was listed for this checkpoint.
Model Classification
Family
TimesFM
Type
time series foundation model
Pretrained time-series model for zero-shot or few-shot forecasting workloads.
Resources
Recommended For
- • Long-context zero-shot forecasting with strong open-model baselines
- • Workloads where point forecasting quality matters more than broad task coverage
Strengths
- • Large open checkpoints with long context windows
- • Efficient patched-transformer design with strong zero-shot behavior
Limitations
- • Primarily a forecasting family rather than a general multi-task TSFM
- • Quantile support is not the main identity of the family
Capabilities
Specifications
- Parameters
- n/a
- Architecture
- Time series transformer with native multivariate and covariate support
- 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
- timesfm-non-commercial-license-v1.0 (weights)