SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

ms-marco-MiniLM-L4-v2 vs ms-marco-MiniLM-L6-v2

Ms-marco-MiniLM-L4-v2 has 19M parameters and ms-marco-MiniLM-L6-v2 has 23M parameters; both are released under Apache License 2.0; at 16-bit, ms-marco-MiniLM-L4-v2 needs about 0 GB (1x MI300X from $1.85 an hour) and ms-marco-MiniLM-L6-v2 about 0.1 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field ms-marco-MiniLM-L4-v2
cross-encoder/ms-marco-MiniLM-L4-v2
ms-marco-MiniLM-L6-v2
cross-encoder/ms-marco-MiniLM-L6-v2
Publisher Sentence Transformers - Cross-Encoders Sentence Transformers - Cross-Encoders
Task Text ranking Text ranking
Modality Other Other
Parameters, as reported 19M parameters 23M parameters
Architecture BertForSequenceClassification BertForSequenceClassification
Library sentence-transformers sentence-transformers
Context length 512 tokens 512 tokens
Repository size 750.7 MB 890.2 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 GB 0.1 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 777b2f369bc1 233902d25c44
Downloads reported by the hub 4.8M 88.6M
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 ms-marco-MiniLM-L6-v2

Once a first-pass search has returned its candidates, this cross-encoder puts them in order, reading the query with each passage and handing them back sorted. At 23M parameters it needs 0.1 GB at 16-bit and rounds to nothing at 8-bit or 4-bit. For $1.85 an hour on demand, the cheapest setup we price is a 192 GB MI300X, a card this ranker would leave almost empty; its sensible home is a corner of a GPU you already pay for.

Apache 2.0 puts no fence around commercial use, so you can retrain it on your query logs and redistribute the result, keeping the license and NOTICE files intact and stating what changed. Two checks: the 512-token context must hold the query and the passage together, and the lineage runs to cross-encoder/ms-marco-MiniLM-L12-v2 with sentence-transformers/msmarco as the training set. Access is open and the files were last updated 2026-08-09.

Questions

Which is larger, ms-marco-MiniLM-L4-v2 or ms-marco-MiniLM-L6-v2?

ms-marco-MiniLM-L6-v2 (23M 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-L4-v2 or ms-marco-MiniLM-L6-v2?

At 4-bit, ms-marco-MiniLM-L4-v2 fits on 1x MI300X from $1.85 an hour and ms-marco-MiniLM-L6-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-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.

Can I use ms-marco-MiniLM-L6-v2 commercially?

Yes. ms-marco-MiniLM-L6-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.

Related Comparisons