SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

chronos-2 vs TimeMoE-50M

Chronos-2 has 119M parameters and TimeMoE-50M has 113M parameters; both are released under Apache License 2.0; at 16-bit, chronos-2 needs about 0.3 GB (1x MI300X from $1.85 an hour) and TimeMoE-50M about 0.3 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field chronos-2
autogluon/chronos-2
TimeMoE-50M
Maple728/TimeMoE-50M
Publisher Autogluon Xiaoming Shi
Task Time series forecasting Time series forecasting
Modality Time series Time series
Parameters, as reported 119M parameters 113M parameters
Architecture Chronos2Model TimeMoeForPrediction
Library chronos-forecasting Not stated
Context length Not stated 4,096 tokens
Repository size 477.9 MB 226.8 MB
Artifact formats safetensors safetensors
License apache-2.0 apache-2.0
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 446753ee48ff
Downloads reported by the hub 8.7M 57.1k
Last observed 2026-09-21 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 is the job here, not text. Chronos-2 takes one series or several related ones with covariates and returns multi-step quantile forecasts without training on your data first. At 119 million parameters it needs 0.3 GB at 16-bit, 0.2 GB of it weights, so the cheapest setup in our figures, a 192 GB MI300X at $1.85 per hour, answers the wrong question. It rides beside whatever else is on the accelerator; 8-bit or 4-bit saves two tenths of a gigabyte.

Apache 2.0 covers commercial use, modification and redistribution, with the license and NOTICE file kept and significant changes stated. Check lineage: it was trained on autogluon/chronos_datasets and Salesforce/GiftEvalPretrain, so keep your evaluation series out of both. No context length is listed and the Index carries no host price, so the running cost is your accelerator time; arXiv:2403.07815 and arXiv:2510.15821 set out the design.

Questions

Which is larger, chronos-2 or TimeMoE-50M?

chronos-2 (119M parameters) is larger than TimeMoE-50M (113M parameters), by the parameter counts their publishers report.

Which is cheaper to run, chronos-2 or TimeMoE-50M?

At 4-bit, chronos-2 fits on 1x MI300X from $1.85 an hour and TimeMoE-50M 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 TimeMoE-50M commercially?

Yes. TimeMoE-50M 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.

Related Comparisons