SAVRN Model Hub · Comparisons
gte-reranker-modernbert-base vs mmarco-mMiniLMv2-L12-H384-v1
Gte-reranker-modernbert-base has 150M parameters and mmarco-mMiniLMv2-L12-H384-v1 has 118M parameters; both are released under Apache License 2.0; at 16-bit, gte-reranker-modernbert-base needs about 0.4 GB (1x MI300X from $1.85 an hour) and mmarco-mMiniLMv2-L12-H384-v1 about 0.3 GB (1x MI300X from $1.85 an hour).
| Field | gte-reranker-modernbert-base Alibaba-NLP/gte-reranker-modernbert-base | mmarco-mMiniLMv2-L12-H384-v1 cross-encoder/mmarco-mMiniLMv2-L12-H384-v1 |
|---|---|---|
| Publisher | Alibaba-NLP | Sentence Transformers - Cross-Encoders |
| Task | Text ranking | Text ranking |
| Modality | Other | Other |
| Parameters, as reported | 150M parameters | 118M parameters |
| Architecture | ModernBertForSequenceClassification | XLMRobertaForSequenceClassification |
| Library | transformers | sentence-transformers |
| Context length | 8,192 tokens | 514 tokens |
| Repository size | 2.5 GB | 4.1 GB |
| Artifact formats | safetensors, onnx | safetensors, onnx, openvino, pytorch |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.4 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 | f7481e605550 | 1427fd652930 |
| Downloads reported by the hub | 2.6M | 2.4M |
| 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.
SAVRN's Notes on mmarco-mMiniLMv2-L12-H384-v1
Put this one behind the search index, not in front of it. It takes a query and candidate passages and ranks them, and because MS MARCO was machine translated into 14 languages for training, the same 118M parameters cover multilingual retrieval. At 16-bit the weights are 0.2 GB and it runs in 0.3 GB, so a 192 GB MI300X at $1.85 an hour is absurd on its own; park it beside whatever embedding or language model already holds the card.
Apache 2.0 covers commercial use, modification and redistribution if the license and NOTICE file travel with it and you state your changes. Two checks: the 514 token context must hold query and passage together, so chunk documents to fit, and the 4.1 GB download spans 23 files in safetensors, ONNX, OpenVINO and PyTorch, so take only the format your runtime loads. The base is mMiniLMv2-L12-H384, trained on unicamp-dl/mmarco.
Questions
Which is larger, gte-reranker-modernbert-base or mmarco-mMiniLMv2-L12-H384-v1?
gte-reranker-modernbert-base (150M parameters) is larger than mmarco-mMiniLMv2-L12-H384-v1 (118M parameters), by the parameter counts their publishers report.
Which is cheaper to run, gte-reranker-modernbert-base or mmarco-mMiniLMv2-L12-H384-v1?
At 4-bit, gte-reranker-modernbert-base fits on 1x MI300X from $1.85 an hour and mmarco-mMiniLMv2-L12-H384-v1 on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
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.
Can I use mmarco-mMiniLMv2-L12-H384-v1 commercially?
Yes. mmarco-mMiniLMv2-L12-H384-v1 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.