SAVRN
Search Contact SAVRN

Open-weight model · Fill mask

bert-large-uncased

by BERT community google-bert/bert-large-uncased

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.

Parameters336M
Context512
Weights7.0 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1M

Runs On

What it takes to serve bert-large-uncased (336M 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 0.7 GB 0.8 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.3 GB 0.4 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.2 GB 0.2 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-large-uncased

Fill mask is the task on the label, so the pretraining is what you buy and the fine-tune is yours to run. It learned English from BookCorpus and Wikipedia, and it is uncased, so english and English read the same to it. At 336 million parameters the 16-bit weights are 0.7 GB with 0.8 GB memory needed, and our cheapest line is one MI300X at $1.85 per hour, a 192 GB card with room for more than two hundred copies.

Apache 2.0 permits commercial use, modification and redistribution; you keep the license, copyright and NOTICE files, state significant changes, and receive an express patent grant from contributors. Before committing: the model card was not written by the team that released the model, and the file carries no reported evaluations, so your own fine-tune is the only measurement you get. The 512-token context caps input length; the paper is arXiv:1810.04805.

SAVRN Research, 2026-09-18

Model Card

By BERT community, published under apache-2.0, revision 6da4b6a26a18.

BERT large model (uncased)

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.

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 (1,168 words)

Configuration

Architecture
BertForMaskedLM
Context length (tokens)
512
Layers
24
Hidden size
1,024
Feed-forward size
4,096
Attention heads
16
Vocabulary size
30,522
Model type
bert

Identity and Version

Repository
google-bert/bert-large-uncased
Publisher
BERT community
Task
Fill mask
Modality
Text
Library
transformers
Parameters
336M parameters
Languages
en
Revision
6da4b6a26a1877e173fca3225479512db81a5e5b
First published
2022-03-02
Last updated
2024-02-19

Files and Weights

12 files, 8.2 GB in total. The weights are 5 files totalling 7.0 GB in bin, h5, msgpack, ot, safetensors.

Weights5 files · 7.0 GB
Configuration1 file · 571 B
Tokenizer3 files · 697.6 KB
Documentation1 file · 9.0 KB
Other1 file · 1.2 GB
Repository1 file · 491 B
Every file
FileTypeSizeSHA-256
flax_model.msgpackWeights1.3 GB 95d8c4223c80
model.safetensorsWeights1.3 GB 28349a5c5733
pytorch_model.binWeights1.3 GB be24b235c461
rust_model.otWeights1.5 GB 9db92b28d6fb
tf_model.h5Weights1.5 GB 81bd49719384
config.jsonConfiguration571 B —
README.mdDocumentation9.0 KB —
whole-word-masking.tar.gzOther1.2 GB 9169b12daff1
.gitattributesRepository491 B —
tokenizer.jsonTokenizer466.1 KB —
tokenizer_config.jsonTokenizer48 B —
vocab.txtTokenizer231.5 KB —

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
7.0 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 published7.0 GB
16-bit0.7 GB
8-bit0.3 GB
4-bit0.2 GB

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

Compare bert-large-uncased

Questions About bert-large-uncased

How much GPU memory does bert-large-uncased need?

About 0.8 GB at 16-bit and 0.2 GB at 4-bit: the weights (336M parameters) plus a working margin. A long context needs more.

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

Yes. bert-large-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-large-uncased's context length?

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

Similar Models

This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR. This model is trained with character-level tokenization and whole word masking. You can use this model for masked language modeling as follows: You can also fine-tune this model on downstream tasks. There is no need to tokenize texts in advance, and you can give raw texts to the tokenizer. The texts are tokenized into character-level tokens by sentencepiece. We used the following corpora for pre-training: - Japanese Wikipedia (as of 20221020, 3.2GB, 27M sentences, 1.3M documents) - Japanese portion of CC-100 (85GB, 619M sentences, 66M documents)…

Open weights cc-by-sa-4.0 330M parameters 512 tokens transformers
View model

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 355M parameters 514 tokens transformers
View model

XLM-RoBERTa model pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. It was introduced in the paper Unsupervised Cross-lingual Representation Learning at Scale by Conneau et al. and first released in this repository. Disclaimer: The team releasing XLM-RoBERTa did not write a model card for this model so this model card has been written by the Hugging Face team. XLM-RoBERTa is a multilingual version of RoBERTa. It is pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. RoBERTa is a transformers model pretrained on a large corpus in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in…

Open weights mit 279M parameters 514 tokens transformers
View model

Model · Fill mask

ModernBERT-large

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 396M parameters 8,192 tokens transformers
View model

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

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