SAVRN
Search Contact SAVRN

Open-weight model · Fill mask

bert-base-multilingual-uncased

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

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.

Parameters168M
Context512
Weights3.0 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads4M

Runs On

What it takes to serve bert-base-multilingual-uncased (168M 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 0.3 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-uncased

Four tenths of a gigabyte in 16-bit. For a 168M-parameter fill-mask model that number settles the hardware question: the cheapest setup we list, one MI300X with 192 GB at $1.85 an hour, would sit nearly idle, so put it on a card you already own as a tenant, or run 8-bit at 0.2 GB. It reads 512 tokens per pass, was pretrained on the 102 largest Wikipedia languages, and is uncased, so english and English look the same to it.

Apache 2.0 clears commercial use and redistribution provided the license, copyright notices and any NOTICE file stay attached and significant changes are stated. The 3.0 GB download spans 10 files in four formats, safetensors, pytorch, jax and tf, and you need only one. The card was written by someone other than the team that released the weights, so the paper, arXiv:1810.04805, is the source to read.

SAVRN Research, 2026-09-18

Model Card

By BERT community, published under apache-2.0, revision 7cbf9a625e29.

BERT multilingual base model (uncased)

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.

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 (1,099 words)

Configuration

Architecture
BertForMaskedLM
Context length (tokens)
512
Layers
12
Hidden size
768
Feed-forward size
3,072
Attention heads
12
Vocabulary size
105,879
Model type
bert

Identity and Version

Repository
google-bert/bert-base-multilingual-uncased
Publisher
BERT community
Task
Fill mask
Modality
Text
Library
transformers
Parameters
168M parameters
Languages
af, sq, ar, an, hy, ast, az, ba
Revision
7cbf9a625e29989f6b9c6c2fa68234c304f7e38f
First published
2022-03-02
Last updated
2024-02-19

Files and Weights

10 files, 3.0 GB in total. The weights are 4 files totalling 3.0 GB in bin, h5, msgpack, safetensors.

Weights4 files · 3.0 GB
Configuration1 file · 625 B
Tokenizer3 files · 2.6 MB
Documentation1 file · 8.9 KB
Repository1 file · 445 B
Every file
FileTypeSizeSHA-256
flax_model.msgpackWeights669.9 MB f710cb055884
model.safetensorsWeights672.2 MB b33adb2b700b
pytorch_model.binWeights672.3 MB 2fec0e2a13cd
tf_model.h5Weights999.4 MB 77d2ed6e3779
config.jsonConfiguration625 B —
README.mdDocumentation8.9 KB —
.gitattributesRepository445 B —
tokenizer.jsonTokenizer1.7 MB —
tokenizer_config.jsonTokenizer48 B —
vocab.txtTokenizer871.9 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
3.0 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 published3.0 GB
16-bit0.3 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-uncased

Questions About bert-base-multilingual-uncased

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

About 0.4 GB at 16-bit and 0.1 GB at 4-bit: the weights (168M parameters) plus a working margin. A long context needs more.

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

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

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

Similar Models

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. 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…

Open weights apache-2.0 179M 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