ms-marco-MiniLM-L2-v2: Open-Weight Model

Runs On

What it takes to serve ms-marco-MiniLM-L2-v2 (16M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

Precision	Cheapest setup	Per hour	Also fits
16-bit	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

SAVRN's Notes on ms-marco-MiniLM-L2-v2

Between the retriever and whatever reads the results is where this one lives: take a query, score it against every candidate passage a system like ElasticSearch pulled back, and sort them. At 16 million parameters and 2 layers, the memory line reads 0.0 GB at every precision, so the hardware decision is a placement decision. The cheapest setup we price is one MI300X with 192 GB at $1.85 an hour, though something this small belongs as a tenant beside a larger workload.

Apache 2.0 applies, so commercial use, modification and redistribution are fine with the notices kept and changes stated. The number to check is 512: that is the context length, and the query and passage go in together, so long passages need chunking upstream. On lineage, this 2-layer model is derived from cross-encoder/ms-marco-MiniLM-L12-v2 and trained on sentence-transformers/msmarco, so compare the L12 version before settling on the smaller one.

SAVRN Research, 2026-09-18

Model Card

By Sentence Transformers - Cross-Encoders, published under apache-2.0, revision 1b5cd67b1520.

Cross-Encoder for MS Marco

This model was trained on the MS Marco Passage Ranking task.

The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. The training code is available here: SBERT.net Training MS Marco

Usage with SentenceTransformers

The usage is easy when you have SentenceTransformers installed. Then you can use the pre-trained models like this:

from sentence_transformers import CrossEncoder

model = CrossEncoder('cross-encoder/ms-marco-MiniLM-L2-v2')
scores = model.predict([
    ("How many people live in Berlin?", "Berlin had a population of 3,520,031 registered inhabitants in an area of 891.82 square kilometers."),
    ("How many people live in Berlin?", "Berlin is well known for its museums."),
])
print(scores)
# [ 8.510401 -4.860082]

Usage with Transformers

Read the full model card (315 words)

Configuration

Architecture: BertForSequenceClassification
Context length (tokens): 512
Layers: 2
Hidden size: 384
Feed-forward size: 1,536
Attention heads: 12
Vocabulary size: 30,522
Model type: bert

Identity and Version

Repository: cross-encoder/ms-marco-MiniLM-L2-v2
Publisher: Sentence Transformers - Cross-Encoders
Task: Text ranking
Modality: Other
Library: sentence-transformers
Parameters: 16M parameters
Languages: en
Revision: 1b5cd67b15209f24824c50370e0397743aa9b787
First published: 2022-03-02
Last updated: 2025-08-29

Files and Weights

23 files, 611.3 MB in total. The weights are 14 files totalling 610.1 MB in bin, msgpack, onnx, safetensors.

Weights14 files · 610.1 MB

Configuration2 files · 926 B

Tokenizer3 files · 944.2 KB

Documentation1 file · 3.7 KB

Other2 files · 239.7 KB

Repository1 file · 790 B

Every file

File	Type	Size	SHA-256
flax_model.msgpack	Weights	62.5 MB	f492c859eee9
model.safetensors	Weights	62.5 MB	88f11fa671e1
onnx/model.onnx	Weights	62.5 MB	97ae94c94faf
onnx/model_O1.onnx	Weights	62.5 MB	3950cd2a22f6
onnx/model_O2.onnx	Weights	62.5 MB	f30614cbddf9
onnx/model_O3.onnx	Weights	62.5 MB	2d8e96771a17
onnx/model_O4.onnx	Weights	31.3 MB	b585f2d0cb5d
onnx/model_qint8_arm64.onnx	Weights	15.8 MB	09fb2faaa61c
onnx/model_qint8_avx512.onnx	Weights	15.8 MB	09fb2faaa61c
onnx/model_qint8_avx512_vnni.onnx	Weights	15.8 MB	09fb2faaa61c
onnx/model_quint8_avx2.onnx	Weights	15.8 MB	2c7f4c682cf9
openvino/openvino_model.bin	Weights	62.5 MB	fc9dc11d808d
openvino/openvino_model_qint8_quantized.bin	Weights	15.8 MB	4d379c8fa5e8
pytorch_model.bin	Weights	62.5 MB	e92ec9f854a5
config.json	Configuration	794 B	—
special_tokens_map.json	Configuration	132 B	—
README.md	Documentation	3.7 KB	—
openvino/openvino_model.xml	Other	87.5 KB	—
openvino/openvino_model_qint8_quantized.xml	Other	152.2 KB	—
.gitattributes	Repository	790 B	—
tokenizer.json	Tokenizer	711.4 KB	—
tokenizer_config.json	Tokenizer	1.3 KB	—
vocab.txt	Tokenizer	231.5 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 610.1 MB

Download from Sentence Transformers - Cross-Encoders

Released by Sentence Transformers - Cross-Encoders through its official repository on Hugging Face. Read the license.

Built From

Derived from cross-encoder/ms-marco-MiniLM-L12-v2
Quantized from cross-encoder/ms-marco-MiniLM-L12-v2
Trained on (disclosed) sentence-transformers/msmarco

Memory Requirements

Precision	Weights in memory
As published	610.1 MB
16-bit	0.0 GB
8-bit	0.0 GB
4-bit	0.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Compare ms-marco-MiniLM-L2-v2

Questions About ms-marco-MiniLM-L2-v2

How much GPU memory does ms-marco-MiniLM-L2-v2 need?

About 0 GB at 16-bit and 0 GB at 4-bit: the weights (16M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run ms-marco-MiniLM-L2-v2 on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use ms-marco-MiniLM-L2-v2 commercially?

Yes. ms-marco-MiniLM-L2-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.

What is ms-marco-MiniLM-L2-v2's context length?

512 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Text ranking

ms-marco-MiniLM-L4-v2

Sentence Transformers - Cross-Encoders

This model was trained on the MS Marco Passage Ranking task. The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. The training code is available here: SBERT.net Training MS Marco The usage is easy when you have SentenceTransformers installed. Then you can use the pre-trained models like this: In the following table, we provide various pre-trained Cross-Encoders together with their performance on the TREC Deep Learning 2019 and the MS Marco Passage Reranking dataset.

Open weights apache-2.0 19M parameters 512 tokens sentence-transformers

View model

Model · Text ranking

ms-marco-MiniLM-L6-v2

Sentence Transformers - Cross-Encoders

This model was trained on the MS Marco Passage Ranking task. The model can be used for Information Retrieval: Given a query, encode the query with all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. The training code is available here: SBERT.net Training MS Marco The usage is easy when you have SentenceTransformers installed. Then you can use the pre-trained models like this: In the following table, we provide various pre-trained Cross-Encoders together with their performance on the TREC Deep Learning 2019 and the MS Marco Passage Reranking dataset.

Open weights apache-2.0 23M parameters 512 tokens sentence-transformers

View model

Model · Text ranking

ms-marco-TinyBERT-L2-v2

Sentence Transformers - Cross-Encoders

This model was trained on the MS Marco Passage Ranking task. The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. The training code is available here: SBERT.net Training MS Marco The usage becomes easier when you have SentenceTransformers installed. Then, you can use the pre-trained models like this: In the following table, we provide various pre-trained Cross-Encoders together with their performance on the TREC Deep Learning 2019 and the MS Marco Passage Reranking dataset.

Open weights apache-2.0 4M parameters 512 tokens sentence-transformers

View model

Model · Text ranking

rerank-indonesia-Q8_0-GGUF

Radhi Fadlillah

This model was converted to GGUF format from madebyaris/rerank-indonesia using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model. Install llama.cpp through brew (works on Mac and Linux) Invoke the llama.cpp server or the CLI. Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with LLAMACURL=1 flag along with other hardware-specific flags (for ex: LLAMACUDA=1 for Nvidia GPUs on Linux).

Open weights apache-2.0 sentence-transformers

View model

Model · Text ranking

ms-marco-MiniLM-L12-v2

Sentence Transformers - Cross-Encoders

This model was trained on the MS Marco Passage Ranking task. The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. The training code is available here: SBERT.net Training MS Marco The usage is easy when you have SentenceTransformers installed. Then you can use the pre-trained models like this: In the following table, we provide various pre-trained Cross-Encoders together with their performance on the TREC Deep Learning 2019 and the MS Marco Passage Reranking dataset.

Open weights apache-2.0 33M parameters 512 tokens sentence-transformers

View model

Model · Text ranking

mxbai-rerank-xsmall-v1

Mixedbread

This is the smallest model in our family of powerful reranker models. You can learn more about the models in our blog post. Currently, the best way to use our models is with the most recent version of sentence-transformers. pip install -U sentence-transformers Let's say you have a query, and you want to rerank a set of documents. You can do that with only one line of code: Install transformers.js npm i @xenova/transformers Let's say you have a query, and you want to rerank a set of documents. In JavaScript, you need to add a function: You can use the large model via our API as follows: The API comes with additional features, such as a continous trained reranker! Check out the docs for more…

Open weights apache-2.0 71M parameters 512 tokens transformers

View model