SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

cross-encoder-russian-msmarco vs gte-reranker-modernbert-base

Cross-encoder-russian-msmarco has 178M parameters and gte-reranker-modernbert-base has 150M parameters; cross-encoder-russian-msmarco is released under MIT License and gte-reranker-modernbert-base under Apache License 2.0; at 16-bit, cross-encoder-russian-msmarco needs about 0.4 GB (1x MI300X from $1.85 an hour) and gte-reranker-modernbert-base about 0.4 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field cross-encoder-russian-msmarco
DiTy/cross-encoder-russian-msmarco
gte-reranker-modernbert-base
Alibaba-NLP/gte-reranker-modernbert-base
Publisher Dmitry Tishencko Alibaba-NLP
Task Text ranking Text ranking
Modality Other Other
Parameters, as reported 178M parameters 150M parameters
Architecture BertForSequenceClassification ModernBertForSequenceClassification
Library sentence-transformers transformers
Context length 512 tokens 8,192 tokens
Repository size 716.7 MB 2.5 GB
Artifact formats safetensors safetensors, onnx
License mit apache-2.0
Access Open weights, no gate Open weights, no gate
Memory at 16-bit (weights and margin) 0.4 GB 0.4 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 9029bab08103 f7481e605550
Downloads reported by the hub 236.4k 2.6M
Last observed 2026-09-18 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 gte-reranker-modernbert-base

After the retriever returns its candidates, something must order them, and that is the job of gte-reranker-modernbert-base. It scores a query and a passage as a pair, with an 8,192 token context, so a long passage is judged whole. It needs 0.4 GB at 16-bit, so on the lowest-priced Index configuration, a lone MI300X at $1.85 per hour with 192 GB, it shares a card with the embedding model at no added hardware cost.

Apache 2.0 clears a commercial ranking service: use, modify, redistribute, keep the notices, state significant changes, take the patent grant. Lineage is the check here. The checkpoint is derived from answerdotai/ModernBERT-base, so read that base model's terms, and the paper on file, arXiv:2308.03281, covers the multi-stage contrastive training method. The 15 files total 2.5 GB in safetensors and ONNX against 0.3 GB of 16-bit weights: budget the download, not the memory.

Questions

Which is larger, cross-encoder-russian-msmarco or gte-reranker-modernbert-base?

cross-encoder-russian-msmarco (178M parameters) is larger than gte-reranker-modernbert-base (150M parameters), by the parameter counts their publishers report.

Which is cheaper to run, cross-encoder-russian-msmarco or gte-reranker-modernbert-base?

At 4-bit, cross-encoder-russian-msmarco fits on 1x MI300X from $1.85 an hour and gte-reranker-modernbert-base on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use cross-encoder-russian-msmarco commercially?

Yes. cross-encoder-russian-msmarco 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.

Can I use gte-reranker-modernbert-base commercially?

Yes. gte-reranker-modernbert-base 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