Amazon logo

Chronos-Bolt (Tiny)

Model directory
amazon/chronos-bolt-tiny

9M params | Upstream checkpoint

Chronos-Bolt Tiny is the smallest checkpoint in Amazon's Chronos-Bolt family, at 9M parameters. It is the cost and latency floor of the line: a probabilistic zero-shot forecaster small enough to favor throughput and price over peak accuracy, aimed squarely at latency-sensitive and high-volume work.

Architecturally it keeps the T5-style encoder-decoder backbone shared across Chronos-Bolt, but swaps token-by-token rollout for direct multi-step quantile prediction over patchified history. Predicting the whole horizon in one pass is what makes Bolt materially faster and lighter than the original autoregressive Chronos line. It is pretrained on nearly 100B time-series observations drawn from large public corpora and synthetic pretraining data, as documented by the official Chronos-Bolt model cards.

Where to run this model

Compute availability, hardware requirements, and pricing depend on the execution provider.

TSFM · Your browser

Run locally with WASM. 34.8 MB download, up to 512 history points and 64 forecast steps. One target series, with P10, P50 and P90 forecasts.

Run in your browser
Hugging Face · Weights & deployment

Get model weights, deployment instructions, and current provider listings.

  • sktime TServe

    self-hosted runtime · Family / provider variant · Source checked 2026-10-06

    Run a model-serving container on your own hardware or compute account. Select the catalog checkpoint and matching runtime image.

Hugging Face provider mappings checked 2026-10-06. No Inference Provider mapping was listed for this checkpoint.

Model Classification

Family

Chronos-Bolt

Type

time series foundation model

Pretrained time-series model for zero-shot or few-shot forecasting workloads.

Training Data

Nearly 100B time-series observations from large public corpora and synthetic pretraining data, as documented by the official Chronos-Bolt model cards.

Recommended For

  • • Fast zero-shot probabilistic forecasting in production APIs
  • • Teams replacing classic Chronos-T5 with lower latency inference

Strengths

  • • Direct multi-step forecasting avoids autoregressive rollout cost
  • • Strong default for quantile forecasts with lightweight serving

Limitations

  • • Focused on forecasting rather than broader multi-task time-series work
  • • Less natural fit when you need model behavior tuned around rich multivariate covariates

Capabilities

forecastingquantile-forecastingzero-shothigh-throughput

Tags

amazonchronosprobabilisticultra-fastcost-efficient

Specifications

Parameters
9M
Architecture
patch-based T5 encoder-decoder with direct multi-step quantile forecasting
Context length
n/a
Max context
n/a
Minimum history
n/a
Recommended history
n/a
Input step
n/a
Required target series
1
Temperature
Ignored
Top P
Ignored
Max output
n/a
License
n/a

Related models