Locara

time-series-forecasting

HF group: Tabular · Status: ❌ not built · candidate v2+

What it is

Numeric series → future values. Foundation models for time series have matured fast (2024-26) and are increasingly LLM-shaped: tokenize values, train transformer, generate forward.

Open-weight models

ModelParamsReleasedLicenseQualityNotes
Chronos-Bolt (Amazon)9-205 M2024Apache-2.0T5-based; tokenises valuesMost mature option; runs on CPU.
Chronos-2200 M2025-10Apache-2.0Univariate + multivariate + covariate300+ forecasts/sec on a single GPU.
TimesFM (Google)200 M2024Apache-2.0Decoder-only, patch-basedStrong zero-shot; trained on 100 B time points.
Lag-Llama~150 M2024Apache-2.0Probabilistic forecastsLlama-style decoder; full distributions.
Moirai (Salesforce)14-311 M2024Apache-2.0Universal forecasterStrong.
Timer-XL (THUML)various2025Apache-2.0Long-horizonNewer entrant.

Infrastructure required

Inference

  • ❌ Encoder-only / encoder-decoder inference (sharing the rail with text-to-embedding since these are encoder-only tokenizer+transformer stacks).

Input

  • Numeric series (Float64 vector + timestamps).
  • Optional covariates (multivariate forecasting).

Output

  • ❌ Future values.
  • ❌ Optional probability distribution (for uncertainty quantification).

Storage

  • ❌ Weights cache.
  • App-side: historical series persisted via locara-storage.

Interaction (IPC + SDK)

  • forecast.predict({ series, horizon }) IPC.

Capabilities (manifest)

  • capabilities.models[] for the forecaster.

Gaps

Whole stack. Listed here so we don’t lose the thread — forecasting is increasingly part of consumer apps (energy, finance, health) and the open-weight options are now genuinely strong. Candidate v2+ when a reference app motivates it.

See also