SAVRN Model Hub · Comparisons
chronos-2 vs MOMENT-1-base
Chronos-2 has 119M parameters and MOMENT-1-base has 113M parameters; chronos-2 is released under Apache License 2.0 and MOMENT-1-base under MIT License; at 16-bit, chronos-2 needs about 0.3 GB (1x MI300X from $1.85 an hour) and MOMENT-1-base about 0.3 GB (1x MI300X from $1.85 an hour).
| Field | chronos-2 autogluon/chronos-2 | MOMENT-1-base AutonLab/MOMENT-1-base |
|---|---|---|
| Publisher | Autogluon | Auton Lab |
| Task | Time series forecasting | Time series forecasting |
| Modality | Time series | Time series |
| Parameters, as reported | 119M parameters | 113M parameters |
| Architecture | Chronos2Model | Not stated |
| Library | chronos-forecasting | transformers |
| Context length | Not stated | Not stated |
| Repository size | 477.9 MB | 907.9 MB |
| Artifact formats | safetensors | safetensors, pytorch |
| License | apache-2.0 | mit |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.3 GB | 0.3 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.1 GB | 0.1 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 60088152a34e | 5e44b0ea2637 |
| Downloads reported by the hub | 5.7M | 44.6k |
| Last observed | 2026-10-09 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on chronos-2
Forecasting, not text: Chronos-2 takes one series or several related ones with covariates and returns multi-step quantile forecasts, zero-shot. At 119M parameters it needs 0.3 GB at 16-bit — 0.2 GB of it weights — so the one 192 GB MI300X at $1.85 an hour we list answers the wrong question. It rides beside whatever else the accelerator serves; 4-bit saves two tenths of a gigabyte.
Apache 2.0 covers commercial use with the patent grant intact, which matters once forecasts feed something you sell. It was trained on autogluon/chronos_datasets and Salesforce/GiftEvalPretrain, so keep your evaluation series out of both. The card's June 5, 2026 update pushes AWS deployment through AutoGluon-Cloud, pandas DataFrames in and forecasts out in three lines. The design is set out in arXiv:2403.07815 and arXiv:2510.15821.
Questions
Which is larger, chronos-2 or MOMENT-1-base?
chronos-2 (119M parameters) is larger than MOMENT-1-base (113M parameters), by the parameter counts their publishers report.
Which is cheaper to run, chronos-2 or MOMENT-1-base?
At 4-bit, chronos-2 fits on 1x MI300X from $1.85 an hour and MOMENT-1-base on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use chronos-2 commercially?
Yes. chronos-2 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.
Can I use MOMENT-1-base commercially?
Yes. MOMENT-1-base is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.