# distilbert-base-multilingual-cased by DistilBERT community Source: https://savrn.com/models/distilbert-base-multilingual-cased Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve distilbert-base-multilingual-cased (135M 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 | 0.3 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 | 0.2 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 25, 2026. [distilbert-base-multilingual-cased on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/distilbert-base-multilingual-cased/gpus) ## SAVRN's Notes on distilbert-base-multilingual-cased This is the distilled version of multilingual BERT: one encoder that covers the Wikipedia languages it was trained on, at 135M parameters and noticeably faster than the original. It is cased, so it treats capitalization as meaningful, which helps with names and acronyms. It is a base model for fine-tuning, not a finished classifier. Apache 2.0 allows commercial use. For new multilingual work, compare it with XLM-RoBERTa and mDeBERTa-v3 base in our catalog, which usually fine-tune to higher accuracy; keep DistilBERT where speed per request matters most. SAVRN Research, 2026-09-18 ## Model Card By DistilBERT community, published under apache-2.0, revision 45c032ab32cc. ### Model Card for DistilBERT base multilingual (cased) ### Table of Contents 1. Model Details 2. Uses 3. Bias, Risks, and Limitations 4. Training Details 5. Evaluation 6. Environmental Impact 7. Citation 8. How To Get Started With the Model ### Model Details ### Model Description This model is a distilled version of the [BERT base multilingual model](https://huggingface.co/bert-base-multilingual-cased/). The code for the distillation process can be found [here](https://github.com/huggingface/transformers/tree/main/examples/research_projects/distillation). 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](https://github.com/google-research/bert/blob/master/multilingual.md#list-of-languages). 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](https://huggingface.co/bert-base-multilingual-cased) to learn more about usage, limitations and potential biases. [Read the full model card (726 words)](https://savrn.com/models/distilbert-base-multilingual-cased/card) ## Configuration Architecture DistilBertForMaskedLM Context length (tokens) 512 Vocabulary size 119,547 Model type distilbert ## Identity and Version Repository distilbert/distilbert-base-multilingual-cased Publisher DistilBERT community Task Fill mask Modality Text Library transformers Parameters 135M parameters Languages af, sq, ar, an, hy, ast, az, ba Revision 45c032ab32cc946ad88a166f7cb282f58c753c2e First published 2022-03-02 Last updated 2024-05-06 ## Files and Weights 10 files, 2.9 GB in total. The weights are 4 files totalling 2.9 GB in bin, h5, onnx, safetensors. Weights4 files · 2.9 GB Configuration1 file · 466 B Tokenizer3 files · 3.0 MB Documentation1 file · 7.3 KB Repository1 file · 399 B Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.onnx | Weights | 909.2 MB | 15e32f6737a3 | | model.safetensors | Weights | 541.8 MB | fcf002be901b | | pytorch_model.bin | Weights | 541.8 MB | 0b528805ec3a | | tf_model.h5 | Weights | 910.7 MB | 633897a53557 | | config.json | Configuration | 466 B | — | | README.md | Documentation | 7.3 KB | — | | .gitattributes | Repository | 399 B | — | | tokenizer.json | Tokenizer | 2.0 MB | — | | tokenizer_config.json | Tokenizer | 49 B | — | | vocab.txt | Tokenizer | 995.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 2.9 GB [Download from DistilBERT community](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) Released by DistilBERT community through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:1910.01108](https://savrn.com/papers/distilbert-a-distilled-version-of-bert-smaller-faster-cheaper-and-lighter) - Described by [arXiv:1910.09700](https://savrn.com/papers/quantifying-the-carbon-emissions-of-machine-learning) - Trained on (disclosed) wikipedia ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 2.9 GB | | 16-bit | 0.3 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 - Quantized from[prompt-injection-guard-multilingual](https://savrn.com/models/prompt-injection-guard-multilingual) - Derived from[prompt-injection-guard-multilingual](https://savrn.com/models/prompt-injection-guard-multilingual) - Derived from[clasificador-titulares-pe](https://savrn.com/models/clasificador-titulares-pe) ## Compare distilbert-base-multilingual-cased - [distilbert-base-multilingual-cased vs ModernBERT-base](https://savrn.com/models/compare/distilbert-base-multilingual-cased-vs-modernbert-base) - [distilbert-base-multilingual-cased vs roberta-base](https://savrn.com/models/compare/distilbert-base-multilingual-cased-vs-roberta-base) ## Questions About distilbert-base-multilingual-cased ### How much GPU memory does distilbert-base-multilingual-cased need? About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (135M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run distilbert-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 distilbert-base-multilingual-cased commercially? Yes. distilbert-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 distilbert-base-multilingual-cased's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Fill mask ### [bert-base-arabertv02](https://savrn.com/models/bert-base-arabertv02) [AUB MIND LAB](https://savrn.com/model-publishers/aubmindlab) 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](https://savrn.com/models/bert-base-arabertv02) 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) Model · Fill mask ### [codebert-python](https://savrn.com/models/codebert-python) [NeuLab @ LTI/CMU](https://savrn.com/model-publishers/neulab) 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](https://savrn.com/models/codebert-python) Model · Fill mask ### [ModernBERT-base](https://savrn.com/models/modernbert-base) [Answer.AI](https://savrn.com/model-publishers/answerdotai) 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](https://savrn.com/models/modernbert-base) Model · Fill mask ### [logun-base](https://savrn.com/models/logun-base) [Heitorrosa](https://savrn.com/model-publishers/heitorrosa) This model is a fine-tuned version of Itau-Unibanco/NorBERTo-base on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 2 - evalbatchsize: 4 - gradientaccumulationsteps: 16 - totaltrainbatchsize: 32 - lrschedulertype: linear - lrschedulerwarmupsteps: 500 - numepochs: 1.5 - mixedprecisiontraining: Native AMP - PEFT 0.20.0 - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 4.0.0 - Tokenizers 0.23.1 Open weights cc-by-nc-sa-4.0 150M parameters 8,192 tokens peft [View model](https://savrn.com/models/logun-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) ## DistilBERT community [All models and datasets](https://savrn.com/model-publishers/distilbert) ## Versions - [45c032ab32cc](https://savrn.com/models/distilbert-base-multilingual-cased/versions/45c032ab32cc) · current 2026-09-18 ## 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 2026-10-20. - [Hugging Face record](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) - [How the hub is built](https://savrn.com/model-hub/methodology)