TimesFM Forecasting

Choose the model/API first

The Python package version is 3.0.2; checkpoint versions are separate.

Upstream identifies 3.0 as the latest model. This skill retains 2.5 as its default local workflow because its Apache-licensed weights have different usage terms. For 3.0 multivariate targets, past-only covariates or Apple MLX, read references/timesfm3.md before adapting code. Authorized Google Cloud services have separate terms; a Cloud entitlement does not change the license of downloaded weights. See the upstream license notice.

Use TimesFM for forecasting an ordered temporal target without task-specific model training. It is not a causal effect estimator, clinical detector, or physics-based climate model. Zero-shot describes fitting; it does not establish absence of benchmark overlap in pretraining or good accuracy in a new domain.

Workflow

1. Establish cadence, units, forecast origin, horizon, known-at-origin covariates, evaluation cutoffs and a naive/seasonal-naive baseline.
2. Validate a sorted, unique, regular time grid. Do not dropna() internal gaps: that changes temporal spacing. Reject nonfinite inputs, or explicitly impute inside each training history. Never fill using held-out future targets.
3. Run python scripts/check_system.py before downloading/loading weights. Its available-RAM and cache-volume thresholds are heuristics, not a guarantee against OOM. Start with batch size 1; measure actual peak usage.
4. Load the chosen checkpoint with a recorded immutable revision. For 2.5, compile explicit positive context/horizon settings; zero does not mean “use the maximum.” Keep patch-rounded context + horizon <=16,384 and horizon <=1,024 when using the continuous quantile head.
5. Forecast, validate shapes/finite values/quantile ordering and export the forecast origin, frequency, configuration and checkpoint revision.
6. Evaluate across rolling origins with preprocessing fitted independently per origin. Report accuracy, interval coverage and interval width by horizon; label quantile intervals nominal until calibrated on relevant data.

Installation

Run in a separate environment. The commands below target the reviewed release. Shell extras and version constraints must be quoted, particularly in zsh.

uv venv .venv-timesfm
uv pip install --python .venv-timesfm/bin/python "timesfm[torch]==3.0.2" numpy pandas
.venv-timesfm/bin/python scripts/check_system.py

Use the current PyTorch installation selector for a CUDA wheel matching the host. The 2.5 loader in this release chooses cuda:0 if CUDA exists, otherwise CPU; detecting MPS does not enable MPS inference. Do not use model.to(...) on the wrapper as if it were an nn.Module. For CPU-only XReg, install jax and scikit-learn alongside the PyTorch profile; the upstream [xreg] extra requests jax[cuda], which is not appropriate for macOS. Flax is a separate optional backend; it is not required by the bundled scripts.

from importlib.metadata import version
import timesfm
print(version("timesfm"))  # package has no guaranteed timesfm.__version__
assert hasattr(timesfm, "TimesFM_2p5_200M_torch")

TimesFM 2.5 quick start

The checkpoint-load examples are illustrative: validation of this refresh used native package code with tiny random models and controlled decode fixtures, without downloading pretrained weights. That verifies mechanics, not accuracy.

import numpy as np
import timesfm

model = timesfm.TimesFM_2p5_200M_torch.from_pretrained(
    "google/timesfm-2.5-200m-pytorch",
    revision="1d952420fba87f3c6dee4f240de0f1a0fbc790e3",
    torch_compile=False,  # avoid compilation startup during an initial smoke run
)
model.compile(timesfm.ForecastConfig(
    max_context=512, max_horizon=128, per_core_batch_size=1,
    normalize_inputs=True, use_continuous_quantile_head=True,

…