Observed arrival · 2026-10-19

Timestral: forecasting from a CSV

timestral.org Visit website

Editorial interest 79/100 Selection signal · not a rating of the site

A browser-based interface for generating probabilistic time-series forecasts with the Timestral 209M model, plus a metered API.

Landing page captured for the 2026-10-19 issue.

For: People testing forecasts from CSV data
Worth noticing: It accepts up to eight numeric columns and says missing values are fine; the public demo depends on a separate Hugging Face Space.

Field notes

The input area comes with a 36-row sample of monthly airline passenger counts, which can be replaced with pasted values or an uploaded CSV. The page says the model handles up to eight numeric columns, optional dates, and missing values. Its linked benchmark describes tests on eight public M4 monthly series and includes code to rerun them; those results are presented by the site.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

○OpenPublic substance visible

$PaidCommerce or pricing visible

✦PrettyNotable craft visible

●ProPolished or operationally mature

◎NicheUnusually specific use

ƒJavaScriptBrowser-side code central

One card from the complete issue

Hargeisa Votes at the Movies

256,398 arrived 1,000 judged 985 catalogued Enter the complete issue