# granite-timeseries-ttm-r2 by IBM Granite: Open-Weight Model Source: https://savrn.com/models/granite-timeseries-ttm-r2 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve granite-timeseries-ttm-r2 (805,280 parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. [granite-timeseries-ttm-r2 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/granite-timeseries-ttm-r2/gpus) ## SAVRN's Notes on granite-timeseries-ttm-r2 TinyTimeMixer is IBM's argument that forecasting does not need a large model. This release has about 805,000 parameters, under one million, and it forecasts multivariate series either zero-shot or after a quick fine-tune. It runs comfortably on a CPU, which makes it practical to forecast millions of series. Apache 2.0 allows commercial use. For capacity, energy or demand planning, it is a fast baseline to beat before spending on anything bigger. SAVRN Research, 2026-09-18 ## Model Card By IBM Granite, published under apache-2.0, revision d6a79570cac0. ### Granite-TimeSeries-TTM-R2 Model Card TinyTimeMixers (TTMs) are compact pre-trained models for Multivariate Time-Series Forecasting, open-sourced by IBM Research. With model sizes starting from 1M params, TTM introduces the notion of the first-ever “tiny” pre-trained models for Time-Series Forecasting. The paper describing TTM was accepted at [NeurIPS 24](https://proceedings.neurips.cc/paper_files/paper/2024/hash/874a4d89f2d04b4bcf9a2c19545cf040-Abstract-Conference.html). TTM outperforms other models demanding billions of parameters in several popular zero-shot and few-shot forecasting benchmarks. TTMs are lightweight forecasters, pre-trained on publicly available time series data with various augmentations. TTM provides state-of-the-art zero-shot forecasts and can easily be fine-tuned for multi-variate forecasts with just 5% of the training data to be competitive. Note that zeroshot, fine-tuning and inference tasks using TTM can easily be executed on 1 GPU or on laptops. [Read the full model card (1,933 words)](https://savrn.com/models/granite-timeseries-ttm-r2/card) ## Configuration Architecture TinyTimeMixerForPrediction Stored precision float32 Model type tinytimemixer ## Identity and Version Repository ibm-granite/granite-timeseries-ttm-r2 Publisher IBM Granite Task Time series forecasting Modality Time series Library granite-tsfm Parameters 805,280 parameters Languages Not stated by the source Revision d6a79570cac0f33d526601cd3a0fc7c80a8f9a2f First published 2024-10-08 Last updated 2025-02-26 ## Files and Weights 8 files, 3.8 MB in total. The weights are 2 files totalling 3.2 MB in bin, safetensors. Weights2 files · 3.2 MB Configuration2 files · 1.6 KB Documentation1 file · 18.2 KB Other2 files · 547.8 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 3.2 MB | a706726a7eb0 | | training_args.bin | Weights | 4.9 KB | 0cefcfb5a528 | | config.json | Configuration | 1.6 KB | — | | generation_config.json | Configuration | 69 B | — | | README.md | Documentation | 18.2 KB | — | | benchmarks.webp | Other | 170.4 KB | — | | ttm_image.webp | Other | 377.4 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 3.2 MB [Download from IBM Granite](https://huggingface.co/ibm-granite/granite-timeseries-ttm-r2) Released by IBM Granite through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:2401.03955](https://savrn.com/papers/tiny-time-mixers-ttms-fast-pre-trained-models-for-enhanced-zero-few-shot-forecasting-of-mu) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 3.2 MB | | 16-bit | 0.0 GB | | 8-bit | 0.0 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About granite-timeseries-ttm-r2 ### How much GPU memory does granite-timeseries-ttm-r2 need? About 0 GB at 16-bit and 0 GB at 4-bit: the weights (805,280 parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run granite-timeseries-ttm-r2 on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use granite-timeseries-ttm-r2 commercially? Yes. granite-timeseries-ttm-r2 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ## Similar Models Model · Time series forecasting ### [granite-timeseries-ttm-r1](https://savrn.com/models/granite-timeseries-ttm-r1) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) TinyTimeMixers (TTMs) are compact pre-trained models for Multivariate Time-Series Forecasting, open-sourced by IBM Research. With less than 1 Million parameters, TTM (accepted in NeurIPS 24) introduces the notion of the first-ever “tiny” pre-trained models for Time-Series Forecasting. TTM outperforms several popular benchmarks demanding billions of parameters in zero-shot and few-shot forecasting. TTMs are lightweight forecasters, pre-trained on publicly available time series data with various augmentations. TTM provides state-of-the-art zero-shot forecasts and can easily be fine-tuned for multi-variate forecasts with just 5% of the training data to be competitive. Refer to our paper for… Open weights apache-2.0 805,280 parameters granite-tsfm [View model](https://savrn.com/models/granite-timeseries-ttm-r1) Model · Time series forecasting ### [granite-timeseries-patchtst](https://savrn.com/models/granite-timeseries-patchtst) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) PatchTST is a transformer-based model for time series modeling tasks, including forecasting, regression, and classification. This repository contains a pre-trained PatchTST model encompassing all seven channels of the ETTh1 dataset. This particular pre-trained model produces a Mean Squared Error (MSE) of 0.3881 on the test split of the ETTh1 dataset when forecasting 96 hours into the future with a historical data window of 512 hours. For training and evaluating a PatchTST model, you can refer to this demo notebook. The PatchTST model was proposed in A Time Series is Worth 64 Words: Long-term Forecasting with Transformers by Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong, Jayant Kalagnanam. At… Open weights apache-2.0 616,032 parameters transformers [View model](https://savrn.com/models/granite-timeseries-patchtst) Model · Time series forecasting ### [granite-timeseries-ttm-r3](https://savrn.com/models/granite-timeseries-ttm-r3) [IBM Granite](https://savrn.com/model-publishers/ibm-granite) Building on top of TTM-R1 and TTM-R2, we introduce the next generation of TinyTimeMixer under the Granite time-series foundation model family — Granite-TTM-R3. This release incorporates several novel tiny-neural architectural innovations designed to push the limits of accuracy in high-speed forecasting, a critical requirement for real-world production deployments. Granite-TTM-R3 is a family of pretrained models supporting multiple real-world forecasting scenarios: - Zero-shot forecasting across unseen datasets - Few-shot adaptation effective with as few as ~1K samples - Full fine-tuning for domain-specific optimization - Multivariate time-series forecasting - Exogenous / control variable… Open weights apache-2.0 1M parameters [View model](https://savrn.com/models/granite-timeseries-ttm-r3) Model · Time series forecasting ### [TiRex](https://savrn.com/models/tirex) [NX-AI](https://savrn.com/model-publishers/nx-ai) This repository provides the pre-trained forecasting model TiRex introduced in the paper TiRex is a 35M parameter pre-trained time series forecasting model based on xLSTM. TiRex is a pre-trained model that performs time series forecasting without requiring any training on your data. Simply download and use it. TiRex provides both point estimates and quantile estimates. - State-of-the-art Performance over Long and Short Horizons: TiRex achieves top scores in various time series forecasting benchmarks, see GiftEval and ChronosZS. These benchmark show that TiRex provides great performance for both long and short-term forecasting. A detailed documentation of TiRex can be found here… Open weights other tirex [View model](https://savrn.com/models/tirex) Model · Time series forecasting ### [TiRex-1.1-gifteval](https://savrn.com/models/tirex-1-1-gifteval) [NX-AI](https://savrn.com/model-publishers/nx-ai) The 1.1 release introduces long period normalisation, a method applied solely during inference. This specific version (1.1-gifteval) includes the 1.1 improvements plus the pretraining dataset has been cleaned to remove overlaps with the GIFT-Eval test dataset. TiRex is a time-series foundation model designed for time series forecasting, with the emphasis to provide state-of-the-art forecasts for both short- and long-term forecasting horizon. TiRex is 35M parameter small and is based on the xLSTM architecture allowing fast and performant forecasts. The model is described in the paper TiRex: Zero-Shot Forecasting across Long and Short Horizons with Enhanced In-Context Learning. TiRex performs… Open weights other tirex [View model](https://savrn.com/models/tirex-1-1-gifteval) Model · Time series forecasting ### [metis-1-preview](https://savrn.com/models/metis-1-preview) [Parisi Labs, Inc.](https://savrn.com/model-publishers/parisi-labs) Metis is Parisi Labs' family of world models for physical systems, starting with energy. Metis 1 Preview is its first generation: probabilistic electricity price forecasts that read prices, load, generation and weather and forecast the full range of what power could cost at a location. This card describes the model. Weights are not distributed; forecasts are served through Ask the Grid, the Forecast API and MCP. Price is the target. Recent real-time prices, published day-ahead prices, load, generation and weather explain what the grid is doing, and every input is lined up to when it was actually available. Responses carry the issue time, quantile bands per interval, the settled price once… Open weights other [View model](https://savrn.com/models/metis-1-preview) ## IBM Granite [All models and datasets](https://savrn.com/model-publishers/ibm-granite) ## Versions - [d6a79570cac0](https://savrn.com/models/granite-timeseries-ttm-r2/versions/d6a79570cac0) · current 2026-09-18 ## Explore More - [All time series forecasting models](https://savrn.com/models/tasks/time-series-forecasting) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [IBM Granite website](https://www.ibm.com/granite) - [Hugging Face record](https://huggingface.co/ibm-granite/granite-timeseries-ttm-r2) - [How the hub is built](https://savrn.com/model-hub/methodology)