# bert-base-uncased by BERT community: Open-Weight Model Source: https://savrn.com/models/bert-base-uncased Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve bert-base-uncased (110M 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](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. [bert-base-uncased on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/bert-base-uncased/gpus) ## SAVRN's Notes on bert-base-uncased Load this at 16-bit and it takes 0.3 GB of the 192 GB on the cheapest card in our table, one MI300X at $1.85 an hour on demand. Nobody buys a card for it; it rides on whatever is already running. The task it ships for is fill mask, the masked language modeling objective it was pretrained on with BookCorpus and Wikipedia, and 512 tokens is the most it takes in one pass. Apache 2.0 covers commercial use, modification and redistribution, provided you keep the license and copyright notices and state what you changed. Worth knowing before you commit: the team that released it never wrote a model card, so the card is secondhand, and the 16 files on disk total 3.45 GB across seven formats, safetensors to Rust, while the 16-bit weights you run are 0.2 GB. Pull one format, not the folder. SAVRN Research, 2026-09-18 ## Model Card By BERT community, published under apache-2.0, revision 86b5e0934494. ### BERT base model (uncased) Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in [this paper](https://savrn.com/papers/bert-pre-training-of-deep-bidirectional-transformers-for-language-understanding) and first released in [this repository](https://github.com/google-research/bert). 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 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 those texts. More precisely, it was pretrained with two objectives: [Read the full model card (1,267 words)](https://savrn.com/models/bert-base-uncased/card) ## Configuration Architecture BertForMaskedLM Context length (tokens) 512 Layers 12 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Vocabulary size 30,522 Model type bert ## Identity and Version Repository google-bert/bert-base-uncased Publisher BERT community Task Fill mask Modality Text Library transformers Parameters 110M parameters Languages en Revision 86b5e0934494bd15c9632b12f734a8a67f723594 First published 2022-03-02 Last updated 2024-02-19 ## Files and Weights 16 files, 3.5 GB in total. The weights are 8 files totalling 3.5 GB in bin, h5, mlmodel, msgpack, onnx, ot, safetensors. Weights8 files · 3.5 GB Configuration2 files · 1.2 KB Tokenizer3 files · 697.6 KB Documentation2 files · 21.9 KB Repository1 file · 491 B Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | coreml/fill-mask/float32_model.mlpackage/Data/com.apple.CoreML/model.mlmodel | Weights | 164.9 KB | — | | coreml/fill-mask/float32_model.mlpackage/Data/com.apple.CoreML/weights/weight.bin | Weights | 531.8 MB | c0c9f4914b4f | | flax_model.msgpack | Weights | 438.1 MB | ea201fabe466 | | model.onnx | Weights | 532.1 MB | 44d7a2896d34 | | model.safetensors | Weights | 440.4 MB | 68d45e234eb4 | | pytorch_model.bin | Weights | 440.5 MB | 097417381d6c | | rust_model.ot | Weights | 534.2 MB | afd9aa425fd4 | | tf_model.h5 | Weights | 536.1 MB | a7a17d6d844b | | config.json | Configuration | 570 B | — | | coreml/fill-mask/float32_model.mlpackage/Manifest.json | Configuration | 617 B | — | | LICENSE | Documentation | 11.4 KB | — | | README.md | Documentation | 10.5 KB | — | | .gitattributes | Repository | 491 B | — | | tokenizer.json | Tokenizer | 466.1 KB | — | | tokenizer_config.json | Tokenizer | 48 B | — | | vocab.txt | Tokenizer | 231.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 3.5 GB [Download from BERT community](https://huggingface.co/google-bert/bert-base-uncased) Released by BERT community through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:1810.04805](https://savrn.com/papers/bert-pre-training-of-deep-bidirectional-transformers-for-language-understanding) - Trained on (disclosed) bookcorpus - Trained on (disclosed) wikipedia ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 3.5 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. ## Built on This Model - Derived from[bert-log-anomaly-detection](https://savrn.com/models/bert-log-anomaly-detection) - Derived from[span-marker-bert-base-uncased-acronyms](https://savrn.com/models/span-marker-bert-base-uncased-acronyms) - Derived from[counterbench-bert-base-uncased](https://savrn.com/models/counterbench-bert-base-uncased) - Derived from[assign5autotrain](https://savrn.com/models/assign5autotrain) - Derived from[finetuned-medical-bert](https://savrn.com/models/finetuned-medical-bert) - Derived from[topic-classification-bert](https://savrn.com/models/topic-classification-bert) - Derived from[bert-base-squad-qa](https://savrn.com/models/bert-base-squad-qa) - Derived from[bert-base-ud-ewt-pos](https://savrn.com/models/bert-base-ud-ewt-pos) - Derived from[bert-base-conll03-ner](https://savrn.com/models/bert-base-conll03-ner) - Derived from[bert-base-agnews-topic-classification](https://savrn.com/models/bert-base-agnews-topic-classification) - Derived from[ft-agnews](https://savrn.com/models/ft-agnews) - Derived from[simcse-bert-uncased-unsup](https://savrn.com/models/simcse-bert-uncased-unsup) - Derived from[simcse-bert-base-snli-unsup](https://savrn.com/models/simcse-bert-base-snli-unsup) - Quantized from[bert-base-uncased-pnn-d50-int8-j21](https://savrn.com/models/bert-base-uncased-pnn-d50-int8-j21) - Derived from[bert-base-uncased-pnn-d50-int8-j21](https://savrn.com/models/bert-base-uncased-pnn-d50-int8-j21) - Derived from[binary-product-review-sentiment-with-distilbert](https://savrn.com/models/binary-product-review-sentiment-with-distilbert) ## Compare bert-base-uncased - [bert-base-uncased vs camembert-base](https://savrn.com/models/compare/bert-base-uncased-vs-camembert-base) - [bert-base-uncased vs juribert-base](https://savrn.com/models/compare/bert-base-uncased-vs-juribert-base) - [bert-base-german-cased vs bert-base-uncased](https://savrn.com/models/compare/bert-base-german-cased-vs-bert-base-uncased) ## Questions About bert-base-uncased ### How much GPU memory does bert-base-uncased need? About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (110M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run bert-base-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-uncased commercially? Yes. bert-base-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-uncased's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Fill mask ### [bert-base-german-cased](https://savrn.com/models/bert-base-german-cased) [BERT community](https://savrn.com/model-publishers/google-bert) 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](https://savrn.com/models/bert-base-german-cased) Model · Fill mask ### [juribert-base](https://savrn.com/models/juribert-base) [DaSciM](https://savrn.com/model-publishers/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](https://savrn.com/models/juribert-base) Model · Fill mask ### [camembert-base](https://savrn.com/models/camembert-base) [ALMAnaCH (Inria)](https://savrn.com/model-publishers/almanach) 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](https://savrn.com/models/camembert-base) Model · Fill mask ### [bert-base-cased](https://savrn.com/models/bert-base-cased) [BERT community](https://savrn.com/model-publishers/google-bert) 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. 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… Open weights apache-2.0 109M parameters 512 tokens transformers [View model](https://savrn.com/models/bert-base-cased) Model · Fill mask ### [bert-base-chinese](https://savrn.com/models/bert-base-chinese) [BERT community](https://savrn.com/model-publishers/google-bert) 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](https://savrn.com/models/bert-base-chinese) Model · Fill mask ### [roberta-base](https://savrn.com/models/roberta-base) [Facebook AI community](https://savrn.com/model-publishers/facebookai) 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](https://savrn.com/models/roberta-base) ## BERT community [All models and datasets](https://savrn.com/model-publishers/google-bert) ## Versions - [86b5e0934494](https://savrn.com/models/bert-base-uncased/versions/86b5e0934494) · current 2026-10-24 ## Explore More - [All fill mask models](https://savrn.com/models/tasks/fill-mask) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [BERT community website](https://github.com/google-research/bert) - [Hugging Face record](https://huggingface.co/google-bert/bert-base-uncased) - [How the hub is built](https://savrn.com/model-hub/methodology)