Open-weight model
granite-timeseries-tspulse-r1
by IBM Granite ibm-granite/granite-timeseries-tspulse-r1
granite-timeseries-tspulse-r1 is an open-weight model from IBM Granite, released under Apache License 2.0. It has 1M parameters. At 16-bit it needs about 0 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 977.5k downloads a month.
TSPulse models are ultra-compact pre-trained models for time-series data, featuring just 1M parameters and supporting GPU-free inference.
Runs On
What it takes to serve granite-timeseries-tspulse-r1 (1M 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 (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x 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, read Oct 12, 2026.
granite-timeseries-tspulse-r1 on every accelerator the SAVRN Index prices, at every precision
Model Card
By IBM Granite, published under apache-2.0, revision 2e64fcdc2a06.
Granite-TimeSeries-TSPulse-R1 Model Card
Update (Mar 2026): TSPulse has been accepted at ICLR 2026.
TSPulse models are ultra-compact pre-trained models for time-series data, featuring just 1M parameters and supporting GPU-free inference. Designed for versatility, TSPulse excels across a wide range of tasks including classification, anomaly detection (AD), imputation, and similarity search.
At the architecture level, TSPulse introduces a novel dual-space masked reconstruction strategy that learns jointly from both time and frequency domains —- capturing complementary patterns in a unified embedding space. This is coupled with a dual-embedding disentanglement mechanism that produces both fine-grained embeddings for detailed analysis and semantic embeddings for broader understanding. These semantic embeddings are inherently robust to variations in time, magnitude, and noise, making them ideal for time-series retrieval.
Configuration
- Architecture
- TSPulseForReconstruction
- Stored precision
- float32
- Model type
- tspulse
Identity and Version
- Repository
- ibm-granite/granite-timeseries-tspulse-r1
- Publisher
- IBM Granite
- Task
- Not stated by the source
- Modality
- Other
- Library
- granite-tsfm
- Parameters
- 1M parameters
- Languages
- Not stated by the source
- Revision
- 2e64fcdc2a06d3565dfadaf0065c0ab5055f80f2
- First published
- 2025-06-03
- Last updated
- 2026-03-07
Files and Weights
5 files, 4.7 MB in total. The weights are 1 file totalling 4.4 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 4.4 MB | 57fa03b67d14 |
| config.json | Configuration | 3.5 KB | — |
| README.md | Documentation | 9.2 KB | — |
| tspulse_overview.webp | Other | 295.3 KB | 2cfc0774815e |
| .gitattributes | Repository | 1.6 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 4.4 MB
Released by IBM Granite through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2505.13033
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 4.4 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-tspulse-r1
How much GPU memory does granite-timeseries-tspulse-r1 need?
About 0 GB at 16-bit and 0 GB at 4-bit: the weights (1M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run granite-timeseries-tspulse-r1 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-tspulse-r1 commercially?
Yes. granite-timeseries-tspulse-r1 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.