# bert-base-multilingual-uncased vs ModernBERT-base Compared Source: https://savrn.com/models/compare/bert-base-multilingual-uncased-vs-modernbert-base Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- | Field | [bert-base-multilingual-uncased](https://savrn.com/models/bert-base-multilingual-uncased) google-bert/bert-base-multilingual-uncased | [ModernBERT-base](https://savrn.com/models/modernbert-base) answerdotai/ModernBERT-base | | --- | --- | --- | | Publisher | BERT community | Answer.AI | | Task | Fill mask | Fill mask | | Modality | Text | Text | | Parameters, as reported | 168M parameters | 150M parameters | | Architecture | BertForMaskedLM | ModernBertForMaskedLM | | Library | transformers | transformers | | Context length | 512 tokens | 8,192 tokens | | Repository size | 3.0 GB | 3.1 GB | | Artifact formats | safetensors, pytorch, jax, tf | safetensors, onnx, pytorch | | License | apache-2.0 | apache-2.0 | | Access | Open weights, no gate | Open weights, no gate | | Memory at 16-bit (weights and margin) | 0.4 GB | 0.4 GB | | Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 | | Memory at 4-bit (weights and margin) | 0.1 GB | 0.1 GB | | Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 | | Revision viewed | 7cbf9a625e29 | 8949b909ec90 | | Downloads reported by the hub | 1.6M | 3.6M | | Last observed | 2026-10-25 | 2026-10-25 | An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking. ## 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 ## SAVRN's Notes on ModernBERT-base Fill mask is the listed task, so treat it as an encoder you train onto a job, retrieval or classification over long documents, not one you talk to. Memory barely enters the hardware decision: 0.3 GB of weights and 0.4 GB needed at 16-bit against the cheapest Index setup, an MI300X with 192 GB at $1.85 an hour on-demand. Size the box for throughput on long inputs, not for the model. Under Apache 2.0 you can fine-tune it, ship the result commercially and redistribute it, provided the license and copyright notices stay attached and significant changes are stated. Before committing, confirm 8,192 tokens covers your longest inputs, and note the stored precision is float32 and the 3.1 GB repository holds three formats, well beyond the 0.3 GB you load. The page shows no reported evaluations and no Index host price; the paper, arXiv:2412.13663, is the only reference. SAVRN Research, 2026-09-18 ## Questions ### Which is larger, bert-base-multilingual-uncased or ModernBERT-base? bert-base-multilingual-uncased (168M parameters) is larger than ModernBERT-base (150M parameters), by the parameter counts their publishers report. ### Which is cheaper to run, bert-base-multilingual-uncased or ModernBERT-base? At 4-bit, bert-base-multilingual-uncased fits on 1x MI300X from $1.85 an hour and ModernBERT-base on 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. ### Can I use ModernBERT-base commercially? Yes. ModernBERT-base 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. ## Related Comparisons - [bert-base-arabertv02 vs bert-base-multilingual-uncased](https://savrn.com/models/compare/bert-base-arabertv02-vs-bert-base-multilingual-uncased) - [bert-base-multilingual-cased vs bert-base-multilingual-uncased](https://savrn.com/models/compare/bert-base-multilingual-cased-vs-bert-base-multilingual-uncased) - [bert-base-arabertv02 vs ModernBERT-base](https://savrn.com/models/compare/bert-base-arabertv02-vs-modernbert-base) - [distilbert-base-multilingual-cased vs ModernBERT-base](https://savrn.com/models/compare/distilbert-base-multilingual-cased-vs-modernbert-base)