ms-marco-electra-base: Open-Weight Model

Runs On

What it takes to serve ms-marco-electra-base (109M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

Precision	Weights	Memory needed	Cheapest setup	Per hour	Also fits
16-bit	0.2 GB	0.3 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	0.1 GB	0.1 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	0.1 GB	0.1 GB	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-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.

SAVRN Research, 2026-09-18

Model Card

By Sentence Transformers - Cross-Encoders, published under apache-2.0, revision 8b9301757513.

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-electra-base')
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)
# [9.9227107e-01 2.0136760e-05]

Usage with Transformers

Read the full model card (314 words)

Configuration

Architecture: ElectraForSequenceClassification
Context length (tokens): 512
Layers: 12
Hidden size: 768
Feed-forward size: 3,072
Attention heads: 12
Vocabulary size: 30,522
Model type: electra

Identity and Version

Repository: cross-encoder/ms-marco-electra-base
Publisher: Sentence Transformers - Cross-Encoders
Task: Text ranking
Modality: Other
Library: sentence-transformers
Parameters: 109M parameters
Languages: en
Revision: 8b9301757513f8a695920c334c3a9f365ebeb357
First published: 2022-03-02
Last updated: 2025-08-29

Files and Weights

23 files, 3.8 GB in total. The weights are 13 files totalling 3.8 GB in bin, onnx, safetensors.

Weights13 files · 3.8 GB

Configuration2 files · 862 B

Tokenizer3 files · 944.2 KB

Documentation1 file · 3.6 KB

Other3 files · 1.2 MB

Repository1 file · 399 B

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	438.0 MB	d13cb549da54
onnx/model.onnx	Weights	438.2 MB	5e3e67422171
onnx/model_O1.onnx	Weights	438.1 MB	759510ff6061
onnx/model_O2.onnx	Weights	438.0 MB	219c2086a10d
onnx/model_O3.onnx	Weights	438.0 MB	0a17242a7a5e
onnx/model_O4.onnx	Weights	219.0 MB	077075bbf7f6
onnx/model_qint8_arm64.onnx	Weights	110.8 MB	c8e4292facfa
onnx/model_qint8_avx512.onnx	Weights	110.8 MB	c8e4292facfa
onnx/model_qint8_avx512_vnni.onnx	Weights	110.8 MB	c8e4292facfa
onnx/model_quint8_avx2.onnx	Weights	110.8 MB	ba6abd7acd1a
openvino/openvino_model.bin	Weights	437.9 MB	ed47c86dd5e2
openvino/openvino_model_qint8_quantized.bin	Weights	110.6 MB	a4ac4a491328
pytorch_model.bin	Weights	438.0 MB	c554473d6145
config.json	Configuration	730 B	—
special_tokens_map.json	Configuration	132 B	—
README.md	Documentation	3.6 KB	—
CEBinaryClassificationEvaluator_MS-Marco_results.csv	Other	5.5 KB	—
openvino/openvino_model.xml	Other	414.6 KB	—
openvino/openvino_model_qint8_quantized.xml	Other	735.9 KB	—
.gitattributes	Repository	399 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: 3.8 GB

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 google/electra-base-discriminator
Quantized from google/electra-base-discriminator
Trained on (disclosed) sentence-transformers/msmarco

Memory Requirements

Precision	Weights in memory
As published	3.8 GB
16-bit	0.2 GB
8-bit	0.1 GB
4-bit	0.1 GB

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

Compare ms-marco-electra-base

Questions About ms-marco-electra-base

How much GPU memory does ms-marco-electra-base need?

About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (109M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run ms-marco-electra-base 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-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.

What is ms-marco-electra-base's context length?

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

Similar Models

Model · Text ranking

qnli-electra-base

Sentence Transformers - Cross-Encoders

This model was trained using SentenceTransformers Cross-Encoder class. Given a question and paragraph, can the question be answered by the paragraph? The models have been trained on the GLUE QNLI dataset, which transformed the SQuAD dataset into an NLI task. For performance results of this model, see [SBERT.net Pre-trained Cross-Encoder][https://www.sbert.net/docs/pretrainedcross-encoders.html]. Pre-trained models can be used like this: You can use the model also directly with Transformers library (without SentenceTransformers library)

Open weights apache-2.0 109M parameters 512 tokens sentence-transformers

View model

Model · Text ranking

mmarco-mMiniLMv2-L12-H384-v1

Sentence Transformers - Cross-Encoders

This model was trained on the MMARCO dataset. It is a machine translated version of MS MARCO using Google Translate. It was translated to 14 languages. In our experiments, we observed that it performs also well for other languages. As a base model, we used the multilingual MiniLMv2 model. 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 easy when you have SentenceTransformers installed. Then, you can use the pre-trained…

Open weights apache-2.0 118M parameters 514 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

Model · Text ranking

gte-reranker-modernbert-base

Alibaba-NLP

We are excited to introduce the gte-modernbert series of models, which are built upon the latest modernBERT pre-trained encoder-only foundation models. The gte-modernbert series models include both text embedding models and rerank models. The gte-modernbert models demonstrates competitive performance in several text embedding and text retrieval evaluation tasks when compared to similar-scale models from the current open-source community. This includes assessments such as MTEB, LoCO, and COIR evaluation. Use with transformers Use with sentence-transformers: Before you start, install the sentence-transformers libraries: Use with transformers.js Additionally, you can also deploy…

Open weights apache-2.0 150M parameters 8,192 tokens transformers

View model

Model · Text ranking

cross-encoder-russian-msmarco

Dmitry Tishencko

This is a sentence-transformers model based on a pre-trained DeepPavlov/rubert-base-cased and finetuned with MS-MARCO Russian passage ranking dataset. The model can be used for Information Retrieval in the Russian language: 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. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you need to get the logits from the…

Open weights mit 178M parameters 512 tokens 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