SAVRN
Search Contact SAVRN

Open-weight model · Fill mask

bert-base-cased

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

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.

Parameters109M
Context512
Weights1.8 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads3.6M

Runs On

What it takes to serve bert-base-cased (109M 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 0.2 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 bert-base-cased

Nobody needs to size a server around 109 million parameters, and the memory line says why: at 16-bit the weights come to 0.2 GB and the model runs in 0.3 GB. The cheapest Index setup, one MI300X with 192 GB at $1.85 an hour on-demand, is the smallest slice we list, not what it asks for. Run it on what you own; it fills masked tokens in English text inside a 512 token window, and capitalization changes its answer.

Apache 2.0 lets you ship it in a commercial product if the license and notice files travel with it and you state significant changes. Check that 512 tokens covers your inputs, that bookcorpus and wikipedia pretraining fits your domain, and that a 2024-02-19 last update is recent enough. The repository runs to 1.8 GB across ten files, holding safetensors, pytorch, jax and tf, so pull the format your stack loads.

SAVRN Research, 2026-09-18

Model Card

By BERT community, published under apache-2.0, revision cd5ef92a9fb2.

BERT base model (cased)

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 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 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 from those texts. More precisely, it was pretrained with two objectives:

Read the full model card (1,159 words)

Configuration

Architecture
BertForMaskedLM
Context length (tokens)
512
Layers
12
Hidden size
768
Feed-forward size
3,072
Attention heads
12
Vocabulary size
28,996
Model type
bert

Identity and Version

Repository
google-bert/bert-base-cased
Publisher
BERT community
Task
Fill mask
Modality
Text
Library
transformers
Parameters
109M parameters
Languages
en
Revision
cd5ef92a9fb2f889e972770a36d4ed042daf221e
First published
2022-03-02
Last updated
2024-02-19

Files and Weights

10 files, 1.8 GB in total. The weights are 4 files totalling 1.8 GB in bin, h5, msgpack, safetensors.

Weights4 files · 1.8 GB
Configuration1 file · 570 B
Tokenizer3 files · 649.3 KB
Documentation1 file · 9.0 KB
Repository1 file · 491 B
Every file
FileTypeSizeSHA-256
flax_model.msgpackWeights433.4 MB 2da0d47987f1
model.safetensorsWeights435.8 MB 1d8bdcee6021
pytorch_model.binWeights435.8 MB d6992b8cd27d
tf_model.h5Weights526.7 MB 0d04ece69d04
config.jsonConfiguration570 B —
README.mdDocumentation9.0 KB —
.gitattributesRepository491 B —
tokenizer.jsonTokenizer435.8 KB —
tokenizer_config.jsonTokenizer49 B —
vocab.txtTokenizer213.4 KB —

License and Download

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

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

Built From

  • Described by arXiv:1810.04805
  • Trained on (disclosed) bookcorpus
  • Trained on (disclosed) wikipedia

Memory Requirements

PrecisionWeights in memory
As published1.8 GB
16-bit0.2 GB
8-bit0.1 GB
4-bit0.1 GB

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

Compare bert-base-cased

Questions About bert-base-cased

How much GPU memory does bert-base-cased 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 bert-base-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-cased commercially?

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

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

Similar Models

Eval data: Conll03 (NER), GermEval14 (NER), GermEval18 (Classification), GNAD (Classification) Update April 3rd, 2020: we updated the vocabulary file on deepset's s3 to conform with the default tokenization of punctuation tokens. For details see the related FARM issue. If you want to use the old vocab we have also uploaded a "deepset/bert-base-german-cased-oldvocab" model. - We trained using Google's Tensorflow code on a single cloud TPU v2 with standard settings. - We trained 810k steps with a batch size of 1024 for sequence length 128 and 30k steps with sequence length 512. Training took about 9 days. - As training data we used the latest German Wikipedia dump (6GB of raw txt files), the…

Open weights mit 110M parameters 512 tokens transformers
View model

Model · Fill mask

bert-base-uncased

BERT 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 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 English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labeling 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…

Open weights apache-2.0 110M parameters 512 tokens transformers
View model

Model · Fill mask

juribert-base

DaSciM

JuriBERT is a set of BERT models (tiny, mini, small and base) pre-trained from scratch on French legal-domain specific corpora. JuriBERT models are pretrained on 6.3GB of legal french raw text from two different sources: the first dataset is crawled from Légifrance and the other one consists of anonymized court’s decisions and the pleadings from the Court of Cassation (mémoires ampliatifs). The latter contains more than 100k long documents from different court cases. It is now on Hugging Face in four different versions with varying number of parameters. JuriBERT was trained and evaluated at École Polytechnique in collaboration with HEC Paris by Stella Douka, Hadi Abdine, Mihcalis…

Open weights mit 111M parameters 512 tokens transformers
View model

Model · Fill mask

camembert-base

ALMAnaCH (Inria)

CamemBERT is a state-of-the-art language model for French based on the RoBERTa model. It is now available on Hugging Face in 6 different versions with varying number of parameters, amount of pretraining data and pretraining data source domains. CamemBERT was trained and evaluated by Louis Martin\, Benjamin Muller\, Pedro Javier Ortiz Suárez\, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah and Benoît Sagot. If you use our work, please cite

Open weights mit 111M parameters 514 tokens transformers
View model

Model · Fill mask

bert-base-chinese

BERT community

This model has been pre-trained for Chinese, training and random input masking has been applied independently to word pieces (as in the original BERT paper). This model can be used for masked language modeling CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). typevocabsize: 2 vocabsize: 21128 numhiddenlayers: 12

Open weights apache-2.0 103M 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