# google-research/timesfm

> TimesFM is a pretrained time-series foundation model from Google Research for forecasting, designed to work zero-shot without task-specific training.

- Magnitude: 1.6 out of 10 — Cooling
- Stars: 34,168 total · +4 stars measured 2026-10-09, 00:11–10:57 UTC, ≈ 11 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2024-04-29 · Last push: 2026-09-29
- GitHub: https://github.com/google-research/timesfm · Homepage: https://research.google/blog/a-decoder-only-foundation-model-for-time-series-forecasting/ · Page: https://gitnova.dev/en/r/google-research/timesfm

## Useful for

- Forecast sales or metrics from historical series without training a custom model
- Get quantile forecast intervals to quantify prediction uncertainty
- Fine-tune the model on your own data via LoRA and HuggingFace PEFT

## Why it’s here

- Star-counter measurements on 2026-10-09 (UTC), 00:11–10:57: 34164 → 34168 stars (+4). This is the change over that interval.
- Estimated end-of-day forecast: about +11 stars, using observed gains and the previous day.
- Interest is fading: the two-day pace is 33% of the previous week and a half.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3,302
- Issues and pull requests: 497
- Watchers: 227
- Average over the last week: 19 per day
- Usual pace: 90 per day
- Latest release: v3.0.0 (2026-08-28)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: 21, 21, 19, 16, 17, 2, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

09-26 2.5, 09-27 2.5, 09-28 2.7, 09-29 2.6, 09-30 2.2, 10-01 2.1, 10-02 1.9, 10-03 2.0, 10-04 1.7, 10-05 1.8, 10-06 1.9, 10-07 1.8, 10-08 1.9, 10-09 1.8

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-09 11:04 UTC, updated every 30 minutes.