RepoRadar
Leave a Tip
Item detail

google-research/timesfm

TimesFM is Google Research's decoder-only foundation model for time-series forecasting with practical code for preprocessing, loading checkpoints, and adapting forecasts across domains.

Open source →Back to radar
Score8.2
Popularity70.0
Riskconditional
TierSilver
Score breakdown
Usefulness7.0
Novelty7.0
Momentum7.0
Maturity7.4
Open-source/build8.4
Evidence7.2
Workflow potential8.6
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for teams working on demand planning, anomaly detection, or operational forecasting who already have MLOps pipelines for time-series data.

Who should use it

ML teams with time-series forecasting workloadsengineering teams testing model baselines for demand or capacity planninganalytics teams with existing PyTorch/JAX or Python pipelines

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

Forecasting outputs are model outputs, not guarantees; keep guardrails and evaluation before business-critical decisions..

Evidence links

Closest alternatives / related signals

modeltime-seriesforecastingfoundation-modelgoogleapache-2