SAVRN Model Hub · Comparisons
ms-marco-MiniLM-L12-v2 vs ms-marco-MiniLM-L4-v2
Ms-marco-MiniLM-L12-v2 has 33M parameters and ms-marco-MiniLM-L4-v2 has 19M parameters; both are released under Apache License 2.0; at 16-bit, ms-marco-MiniLM-L12-v2 needs about 0.1 GB (1x MI300X from $1.85 an hour) and ms-marco-MiniLM-L4-v2 about 0 GB (1x MI300X from $1.85 an hour).
| Field | ms-marco-MiniLM-L12-v2 cross-encoder/ms-marco-MiniLM-L12-v2 | ms-marco-MiniLM-L4-v2 cross-encoder/ms-marco-MiniLM-L4-v2 |
|---|---|---|
| Publisher | Sentence Transformers - Cross-Encoders | Sentence Transformers - Cross-Encoders |
| Task | Text ranking | Text ranking |
| Modality | Other | Other |
| Parameters, as reported | 33M parameters | 19M parameters |
| Architecture | BertForSequenceClassification | BertForSequenceClassification |
| Library | sentence-transformers | sentence-transformers |
| Context length | 512 tokens | 512 tokens |
| Repository size | 1.3 GB | 750.7 MB |
| Artifact formats | safetensors, onnx, openvino, pytorch, jax | safetensors, onnx, openvino, pytorch, jax |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.1 GB | 0 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0 GB | 0 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 7b0235231ca2 | 777b2f369bc1 |
| Downloads reported by the hub | 1.8M | 4.8M |
| 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 ms-marco-MiniLM-L12-v2
Put this behind the search box, after retrieval. A cross-encoder scores a query against each candidate passage, so you pull candidates with something like Elasticsearch and let this model order them. Trained on the MS MARCO passage ranking task, it carries 33 million parameters and needs 0.1 GB of memory at 16-bit. A 192 GB MI300X at $1.85 an hour, the cheapest fit we list, is a mismatch of scale, so this rides on a card already doing other work.
The license is Apache 2.0, with the usual obligations: keep the license and NOTICE file attached and state significant changes. Start with the 512 token limit: query plus passage must fit inside it, so long passages get chunked before scoring. Second, lineage: it derives from microsoft/MiniLM-L12-H384-uncased and trained on sentence-transformers/msmarco, so test ranking on your own documents. It ships in safetensors, ONNX, OpenVINO, PyTorch and JAX formats.
Questions
Which is larger, ms-marco-MiniLM-L12-v2 or ms-marco-MiniLM-L4-v2?
ms-marco-MiniLM-L12-v2 (33M parameters) is larger than ms-marco-MiniLM-L4-v2 (19M parameters), by the parameter counts their publishers report.
Which is cheaper to run, ms-marco-MiniLM-L12-v2 or ms-marco-MiniLM-L4-v2?
At 4-bit, ms-marco-MiniLM-L12-v2 fits on 1x MI300X from $1.85 an hour and ms-marco-MiniLM-L4-v2 on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use ms-marco-MiniLM-L12-v2 commercially?
Yes. ms-marco-MiniLM-L12-v2 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-MiniLM-L4-v2 commercially?
Yes. ms-marco-MiniLM-L4-v2 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.