TimesFM

Google Research’s foundation model for time-series forecasting. The variant this wiki has documentation for is google/timesfm-2.5-200m-pytorch: a 200-million-parameter transformer, installed with pip install timesfm[torch] and loaded through TimesFM_2p5_200M_torch.from_pretrained (timesfm-2-5-forecasting-tutorial).

Two hundred million parameters is small enough to be a footnote in a language-model context and is the whole model here, which is the first thing worth noticing about this class: a foundation model for numeric sequences doesn’t need to carry the world’s text.

What it does at inference

• Zero-shot. Point it at a series it has never seen and ask for a forecast. No fine-tuning step, no target-dataset training.
• Probabilistic by default. Every forecast returns ten quantiles (q10–q90 plus the mean) rather than a single line, with fix_quantile_crossing=True keeping the intervals monotonic. The intervals are what make the anomaly-detection use possible at all.
• Bounded context and horizon. Compiled with max_context (tested to 1,024 steps, required to be a multiple of 32) and max_horizon (direct to 256; longer via recursive chunking, at a cost in accumulated error).
• Covariates through XReg. Dynamic numerical, dynamic categorical and static categorical regressors can be fused before or after the forecast (xreg_mode), which is how a univariate model gets told about a promotion.
• Compile-time configuration. normalize_inputs, per_core_batch_size, use_continuous_quantile_head, force_flip_invariance, infer_is_positive — the accuracy/cost trade-offs are set when the model is compiled, not per call.

Why a zero-shot forecaster matters to this spoke

fine-tuning carries the corpus’s “don’t reach for fine-tuning first” rule. TimesFM is the limit case of it: the intended path is no adaptation at all, on a task where the classical answer was to fit a fresh model per series — an ARIMA or ETS or gradient-boosted model estimated on that store’s own history. A pretrained forecaster inverts that: one model, many series, nothing fitted.

That is the same move language models made, arriving late in a field that had decades of per-series statistics, and it makes forecasting the clearest non-text place to watch whether the pretrain-once-apply-everywhere pattern actually generalizes. This wiki cannot yet say whether it does — see time-series-forecasting for what evidence would settle it, and note that the only source here measured the model on data it invented.

Snapshot caveat: version numbers, checkpoint names and configuration flags move; everything above is the 2.5 / 200M PyTorch build as documented on 2026-08-03. The model comes from ../llm-providers-wiki’s google, which that spoke owns as an entity.

Related

timesfm-2-5-forecasting-tutorial · time-series-forecasting · fine-tuning · machine-learning · synthesis