SAVRN Model Hub · Comparisons
mmarco-mMiniLMv2-L12-H384-v1 vs ms-marco-electra-base
Mmarco-mMiniLMv2-L12-H384-v1 has 118M parameters and ms-marco-electra-base has 109M parameters; both are released under Apache License 2.0; at 16-bit, mmarco-mMiniLMv2-L12-H384-v1 needs about 0.3 GB (1x MI300X from $1.85 an hour) and ms-marco-electra-base about 0.3 GB (1x MI300X from $1.85 an hour).
| Field | mmarco-mMiniLMv2-L12-H384-v1 cross-encoder/mmarco-mMiniLMv2-L12-H384-v1 | ms-marco-electra-base cross-encoder/ms-marco-electra-base |
|---|---|---|
| Publisher | Sentence Transformers - Cross-Encoders | Sentence Transformers - Cross-Encoders |
| Task | Text ranking | Text ranking |
| Modality | Other | Other |
| Parameters, as reported | 118M parameters | 109M parameters |
| Architecture | XLMRobertaForSequenceClassification | ElectraForSequenceClassification |
| Library | sentence-transformers | sentence-transformers |
| Context length | 514 tokens | 512 tokens |
| Repository size | 4.1 GB | 3.8 GB |
| Artifact formats | safetensors, onnx, openvino, pytorch | 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) | 0.3 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 | 1427fd652930 | 8b9301757513 |
| Downloads reported by the hub | 2.4M | 531.6k |
| 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 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.
SAVRN's Notes on ms-marco-electra-base
Retrieve first, then re-rank. ms-marco-electra-base is the second step: you pair the query with each candidate passage a first-stage search returned, it scores every pair, and you sort by score. At 16-bit the weights are 0.2 GB and it needs 0.3 GB; at 8-bit both round to 0.1 GB. The cheapest listing, a single 192 GB MI300X at $1.85 an hour on demand, is more card than a 109M parameter reranker needs, so we size on candidates scored per second, not memory.
The license is Apache 2.0: commercial use, modification and redistribution are permitted, the license and copyright notices stay, significant changes get stated, and there is an express patent grant. Check lineage: it is derived from google/electra-base-discriminator and trained on sentence-transformers/msmarco, so its sense of relevance comes from MS MARCO passage ranking. The 512-token context holds query and passage together, so long passages get cut first.
Questions
Which is larger, mmarco-mMiniLMv2-L12-H384-v1 or ms-marco-electra-base?
mmarco-mMiniLMv2-L12-H384-v1 (118M parameters) is larger than ms-marco-electra-base (109M parameters), by the parameter counts their publishers report.
Which is cheaper to run, mmarco-mMiniLMv2-L12-H384-v1 or ms-marco-electra-base?
At 4-bit, mmarco-mMiniLMv2-L12-H384-v1 fits on 1x MI300X from $1.85 an hour and ms-marco-electra-base on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
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.
Can I use ms-marco-electra-base commercially?
Yes. ms-marco-electra-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.