SAVRN
Search Contact SAVRN

Open-weight model · Fill mask

bert-base-multilingual-cased

by BERT community google-bert/bert-base-multilingual-cased

Pretrained model on the top 104 languages with the largest Wikipedia using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository.

Parameters179M
Context512
Weights3.2 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1.9M

Runs On

What it takes to serve bert-base-multilingual-cased (179M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.4 GB 0.4 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.2 GB 0.2 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 bert-base-multilingual-cased

Nothing in the memory line will drive a hardware decision. The 16-bit weights are 0.4 GB and the model needs 0.4 GB to run; 8-bit takes 0.2 GB and 4-bit 0.1 GB, so the cheapest setup we list, one MI300X with 192 GB at $1.85 an hour on-demand, is priced for a different class of model. It predicts masked words, case-sensitive, in the 104 languages with the largest Wikipedias, and the hardware question is throughput per dollar, not fit.

Apache 2.0 clears commercial use, modification and redistribution; keep the license, the copyright notices and any NOTICE file, and state significant changes. Three checks before you build on it. The 512-token context caps passage length. The only training data on record is Wikipedia. And the repository holds 3.2 GB across four formats, safetensors, pytorch, jax and tf, when the 16-bit weights you need are 0.4 GB.

SAVRN Research, 2026-09-18

Model Card

By BERT community, published under apache-2.0, revision 3f076fdb1ab6.

BERT multilingual base model (cased)

Pretrained model on the top 104 languages with the largest Wikipedia using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is case sensitive: it makes a difference between english and English.

Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by the Hugging Face team.

Model description

BERT is a transformers model pretrained on a large corpus of multilingual data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was pretrained with two objectives:

Read the full model card (883 words)

Configuration

Architecture
BertForMaskedLM
Context length (tokens)
512
Layers
12
Hidden size
768
Feed-forward size
3,072
Attention heads
12
Vocabulary size
119,547
Model type
bert

Identity and Version

Repository
google-bert/bert-base-multilingual-cased
Publisher
BERT community
Task
Fill mask
Modality
Text
Library
transformers
Parameters
179M parameters
Languages
af, sq, ar, an, hy, ast, az, ba
Revision
3f076fdb1ab68d5b2880cb87a0886f315b8146f8
First published
2022-03-02
Last updated
2024-02-19

Files and Weights

10 files, 3.2 GB in total. The weights are 4 files totalling 3.2 GB in bin, h5, msgpack, safetensors.

Weights4 files · 3.2 GB
Configuration1 file · 625 B
Tokenizer3 files · 3.0 MB
Documentation1 file · 7.1 KB
Repository1 file · 445 B
Every file
FileTypeSizeSHA-256
flax_model.msgpackWeights711.9 MB ebee9a143c50
model.safetensorsWeights714.3 MB 876f584f15eb
pytorch_model.binWeights714.3 MB 3496a508a9a3
tf_model.h5Weights1.1 GB 8c6fe40eebca
config.jsonConfiguration625 B —
README.mdDocumentation7.1 KB —
.gitattributesRepository445 B —
tokenizer.jsonTokenizer2.0 MB —
tokenizer_config.jsonTokenizer49 B —
vocab.txtTokenizer995.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
3.2 GB
Download from BERT community

Released by BERT community through its official repository on Hugging Face. Read the license.

Built From

Memory Requirements

PrecisionWeights in memory
As published3.2 GB
16-bit0.4 GB
8-bit0.2 GB
4-bit0.1 GB

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

Compare bert-base-multilingual-cased

Questions About bert-base-multilingual-cased

How much GPU memory does bert-base-multilingual-cased need?

About 0.4 GB at 16-bit and 0.1 GB at 4-bit: the weights (179M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run bert-base-multilingual-cased 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 bert-base-multilingual-cased commercially?

Yes. bert-base-multilingual-cased 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 bert-base-multilingual-cased's context length?

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

Similar Models

Pretrained model on the top 102 languages with the largest Wikipedia using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is uncased: it does not make a difference between english and English. Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by the Hugging Face team. BERT is a transformers model pretrained on a large corpus of multilingual data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process…

Open weights apache-2.0 168M parameters 512 tokens transformers
View model

Model · Fill mask

ModernBERT-base

Answer.AI

ModernBERT is a modernized bidirectional encoder-only Transformer model (BERT-style) pre-trained on 2 trillion tokens of English and code data with a native context length of up to 8,192 tokens. ModernBERT leverages recent architectural improvements such as: - Rotary Positional Embeddings (RoPE) for long-context support. - Local-Global Alternating Attention for efficiency on long inputs. - Unpadding and Flash Attention for efficient inference. ModernBERT’s native long context length makes it ideal for tasks that require processing long documents, such as retrieval, classification, and semantic search within large corpora. The model was trained on a large corpus of text and code, making it…

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

Model · Fill mask

bert-base-arabertv02

AUB MIND LAB

AraBERT is an Arabic pretrained language model based on Google's BERT architechture. AraBERT uses the same BERT-Base config. More details are available in the AraBERT Paper and in the AraBERT Meetup There are two versions of the model, AraBERTv0.1 and AraBERTv1, with the difference being that AraBERTv1 uses pre-segmented text where prefixes and suffixes were split using the Farasa Segmenter. We evaluate AraBERT models on different downstream tasks and compare them to mBERT), and other state of the art models (To the extent of our knowledge). The Tasks were Sentiment Analysis on 6 different datasets (HARD, ASTD-Balanced, ArsenTD-Lev, LABR), Named Entity Recognition with the ANERcorp, and…

Open weights 136M parameters 512 tokens transformers
View model

This model is a distilled version of the BERT base multilingual model. The code for the distillation process can be found here. This model is cased: it does make a difference between english and English. The model is trained on the concatenation of Wikipedia in 104 different languages listed here. The model has 6 layers, 768 dimension and 12 heads, totalizing 134M parameters (compared to 177M parameters for mBERT-base). On average, this model, referred to as DistilmBERT, is twice as fast as mBERT-base. We encourage potential users of this model to check out the BERT base multilingual model card to learn more about usage, limitations and potential biases. You can use the raw model for either…

Open weights apache-2.0 135M parameters 512 tokens transformers
View model

Model · Fill mask

roberta-base

Facebook AI community

Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is case-sensitive: it makes a difference between english and English. Disclaimer: The team releasing RoBERTa did not write a model card for this model so this model card has been written by the Hugging Face team. RoBERTa is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels…

Open weights mit 125M parameters 514 tokens transformers
View model

Model · Fill mask

codebert-python

NeuLab @ LTI/CMU

This is a microsoft/codebert-base-mlm model, trained for 1,000,000 steps (with batchsize=32) on Python code from the codeparrot/github-code-clean dataset, on the masked-language-modeling task. It is intended to be used in CodeBERTScore: https://github.com/neulab/code-bert-score, but can be used for any other model or task. If you use this model for research, please cite

Open weights 125M parameters 514 tokens transformers
View model