IBM Research has released Granite-TTM-R3, the third generation of its TinyTimeMixer time-series models. Published under the Apache-2.0 license, R3 adds expert routing, trend-residual decomposition, probabilistic forecasts, and an architecture designed for high-throughput inference on CPUs and GPUs.

R3 matters for teams that forecast thousands of products, sensors, or energy meters. IBM reports hundreds of forecast samples per second on CPU, which could reduce infrastructure costs and simplify deployments that currently depend on GPUs. The paper and full ablation studies remain pending, so the published results should be treated as vendor-reported benchmarks.

Granite-TTM architecture for zero-shot and few-shot forecasting
Granite-TTM supports pretrained zero-shot inference and adaptation to new datasets.

Small experts, routed per series

TinyTimeMixer models are compact pretrained networks for multivariate time-series forecasting. R3 retains parameter counts between roughly 1 million and 35 million, while Lite configurations range from 1 million to 18 million parameters.

R3 organizes those models as experts of different sizes. A lightweight router selects or blends experts according to the input series, allowing the system to match model capacity to the data. The backbone uses linear gated attention to capture temporal relationships and contains no self-attention blocks, reducing memory use and computation.

IBM also introduced several changes to training and forecast generation:

  • Trend-residual decomposition: The model separates slow-moving trends from higher-frequency residuals, learns each component, and then trains them jointly.
  • Three-stage pretraining: Trend, residual, and joint training stages are intended to improve convergence stability.