@oragnes: Google quietly open-sourced the time-series forecasting base model TimesFM 2.5—params down to 200 M, context up to 16 k. Feed it raw history and get instant zero-shot forecasts; perfect for crypto predictions, fam 😂
Summary
Google open-sourced TimesFM 2.5, a 200 M-parameter, 16 k-context zero-shot time-series forecasting base model that works straight out of the box on historical data.
View Cached Full Text
Cached at: 04/21/26, 07:56 AM
Google quietly open-sourced its time-series forecasting backbone TimesFM 2.5—parameters down to 200 M, context length up to 16 k. Feed it historical numbers and it spits out zero-shot forecasts. Go build a crypto-coin predictor, fam~
TimesFM is a ready-made, pre-trained foundation model for time-series forecasting. Hand it a sequence of historical values and it will run zero-shot right away.
Similar Articles
@IndieDevHailey: Google quietly releases time series nuclear weapon TimesFM: Predict the future in 5 minutes! Sales forecasting, stock price trends, website traffic, energy load, cryptocurrency volatility... These headache-inducing future numbers now have a unified answer. TimesFM: → Trained on 100 billion real-world time series data...
Google has released TimesFM, a time series forecasting model trained on 100 billion real-world time series data, supporting zero-shot prediction. It is free, open-source, and can run locally on ordinary computers.
google-research/timesfm
Google Research releases TimesFM 2.5, an open-source time-series foundation model for forecasting, with 200M parameters, 16k context length, and support for quantile forecasts up to 1k horizon. The model is available on PyPI and Hugging Face, with fine-tuning via LoRA and integration into Google products like BigQuery ML, Google Sheets, and Vertex Model Garden.
@nicos_ai: GOOGLE HAS SILENTLY RELEASED AN AI THAT PREDICTS PATTERNS Sales. Market prices. Web traffic. Energy demand. Crypto vola…
Google has released TimesFM, an AI model for zero-shot time series forecasting, trained on 100 billion real data points, free and open-source.
TimesFM-3: A zero-shot foundation model for multivariate forecasting
Google introduces TimesFM-3, a state-of-the-art zero-shot foundation model for multivariate time series forecasting, capable of handling multiple targets and covariates in a single forward pass without fine-tuning.
google/timesfm-3.0-pytorch
TimesFM 3.0 is a pretrained time-series foundation model by Google Research, released on Hugging Face with PyTorch weights for time-series forecasting tasks.