TimesFM 2.0 500M

TimesFM 2.0 500M is Google's larger open TimesFM checkpoint for zero-shot time-series forecasting, at 500M parameters. It is the higher-capacity, quality-tier member of the TimesFM line, focused primarily on univariate point forecasting with strong long-context behavior.

Architecturally it is a decoder-only patched transformer (the TimesFmModelForPrediction setup): history is split into patches and decoded into a forecast horizon. The base model targets point forecasts, with optional experimental quantile heads that Google notes are not calibrated after pretraining. Its pretraining builds on the TimesFM family corpus plus an added LOTSA subset listed by the official model card, on top of the broader Google Trends, Wikimedia Pageviews, and synthetic mixture used across the TimesFM line.

On TSFM.ai it is served with a 2,048-point context budget and Google's coarse frequency buckets spanning hourly-through-daily, weekly-through-monthly, and quarterly-plus series. Reach for it when point-forecast quality and capacity matter more than broad task coverage; step down to TimesFM 2.5 200M when you want a cheaper, faster long-context forecaster, and note that quantile support is not the main identity of this family.