TimesFM Models by Google
1 model2026
Last refreshed 2026-09-01. Next refresh: weekly.
Details
ResearcherGoogle
LicenseNoncommercial
Commercial useCommercial use: non-commercial
Models1
Released2026
About
TimesFM is Google Research's family of decoder-only time-series foundation models for zero-shot forecasting. Earlier checkpoints (through TimesFM-2.5) were univariate; TimesFM-3 adds native multivariate forecasting with past and past-future covariates. Public checkpoints are on Hugging Face; GitHub code is Apache-2.0. BigQuery AI.FORECAST currently documents TimesFM-2.5; TimesFM-3 BigQuery integration is described as coming, not live.
Decision facts
- Best fit
- forecastingcodingagent workflows
- Capability starting point
- TimesFM-3
- Lowest tracked input
- Not tracked
- Closest related family
- Google Cloud Text-to-Speech
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
TimesFM-3Current
Use when the workload needs forecasting and 330M parameters.
2026-08forecasting330M parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| TimesFM-3 | Use when the workload needs forecasting and 330M parameters. | 2026-08 | forecasting330M parameters | Current |
Release Timeline
1 release group2026-08
1 current
TimesFM-3
Currentforecasting330M parameters
Specifications(1 models)
| Model | Released | Parameters |
|---|---|---|
| TimesFM-3 | 2026-08 | 330M |