SAVRN Model Hub · Comparisons
bert-large-uncased vs roberta-large
Bert-large-uncased has 336M parameters and roberta-large has 355M parameters; bert-large-uncased is released under Apache License 2.0 and roberta-large under MIT License; at 16-bit, bert-large-uncased needs about 0.8 GB (1x MI300X from $1.85 an hour) and roberta-large about 0.9 GB (1x MI300X from $1.85 an hour).
| Field | bert-large-uncased google-bert/bert-large-uncased | roberta-large FacebookAI/roberta-large |
|---|---|---|
| Publisher | BERT community | Facebook AI community |
| Task | Fill mask | Fill mask |
| Modality | Text | Text |
| Parameters, as reported | 336M parameters | 355M parameters |
| Architecture | BertForMaskedLM | RobertaForMaskedLM |
| Library | transformers | transformers |
| Context length | 512 tokens | 514 tokens |
| Repository size | 8.2 GB | 7.5 GB |
| Artifact formats | safetensors, pytorch, jax, rust, tf | safetensors, onnx, pytorch, jax, tf |
| License | apache-2.0 | mit |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.8 GB | 0.9 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.2 GB | 0.2 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 6da4b6a26a18 | 722cf37b1afa |
| Downloads reported by the hub | 1M | 6.7M |
| Last observed | 2026-10-02 | 2026-10-09 |
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-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's Notes on roberta-large
Loaded at 16-bit, roberta-large needs 0.9 GB of memory for 0.7 GB of weights, and the cheapest setup the SAVRN Index prices for it is one MI300X with 192 GB at $1.85 per hour on demand. Two hundred copies would fit on that card, so the hardware question is not whether it fits but how many instances you stack per accelerator. The job is fill mask on case-sensitive English text: 355M parameters across 24 layers predict a masked token.
MIT is as light as a license gets: commercial use, modification and redistribution, with the copyright and permission notices kept in the package. Context is 514 tokens, so longer documents get chunked first. The 7.5 GB of files spans five formats, safetensors, ONNX, PyTorch, JAX and TensorFlow; pull the one your serving stack loads. Pretraining data was BookCorpus and Wikipedia, English only; the method is in arXiv:1907.11692.
Questions
Which is larger, bert-large-uncased or roberta-large?
roberta-large (355M parameters) is larger than bert-large-uncased (336M parameters), by the parameter counts their publishers report.
Which is cheaper to run, bert-large-uncased or roberta-large?
At 4-bit, bert-large-uncased fits on 1x MI300X from $1.85 an hour and roberta-large on 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.
Can I use roberta-large commercially?
Yes. roberta-large is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.