SAVRN
Search Contact SAVRN

SAVRN Model Hub · Comparisons

deberta-v2-large-japanese-char-wwm vs xlm-roberta-base

Deberta-v2-large-japanese-char-wwm has 330M parameters and xlm-roberta-base has 279M parameters; deberta-v2-large-japanese-char-wwm is released under Creative Commons Attribution-ShareAlike 4.0 and xlm-roberta-base under MIT License; at 16-bit, deberta-v2-large-japanese-char-wwm needs about 0.8 GB (1x MI300X from $1.85 an hour) and xlm-roberta-base about 0.7 GB (1x MI300X from $1.85 an hour).

Published metadata for 2 models, each read from its own repository.
Field deberta-v2-large-japanese-char-wwm
ku-nlp/deberta-v2-large-japanese-char-wwm
xlm-roberta-base
FacebookAI/xlm-roberta-base
Publisher Language Media Processing Lab at Kyoto University Facebook AI community
Task Fill mask Fill mask
Modality Text Text
Parameters, as reported 330M parameters 279M parameters
Architecture DebertaV2ForMaskedLM XLMRobertaForMaskedLM
Library transformers transformers
Context length 512 tokens 514 tokens
Repository size 2.6 GB 6.4 GB
Artifact formats safetensors, pytorch safetensors, onnx, pytorch, jax, tf
License cc-by-sa-4.0 mit
Access Open weights, no gate Open weights, no gate
Memory at 16-bit (weights and margin) 0.8 GB 0.7 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 547b0e8b044f e73636d4f797
Downloads reported by the hub 364.3k 21.5M
Last observed 2026-09-18 2026-09-18

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 xlm-roberta-base

Fill-mask work across 100 languages is where this model earns its place, and the memory math barely registers. At 16-bit the weights are 0.6 GB and the run needs 0.7 GB; the cheapest setup in our table is one MI300X with 192 GB at $1.85 an hour on-demand, leaving nearly all of that card idle. At 8-bit the need is 0.3 GB. With 279M parameters over 12 layers, it fits anywhere a few hundred megabytes of accelerator memory are free.

MIT terms permit commercial use, modification and redistribution; the one obligation is keeping the copyright and permission notices with the files. Check two things before committing: the 514-token context caps each input, and the 6.35 GB download spans 11 files in five formats, so you need only a fraction of it. The page lists no reported evaluations and no host prices, and the last update was February 2024.

Questions

Which is larger, deberta-v2-large-japanese-char-wwm or xlm-roberta-base?

deberta-v2-large-japanese-char-wwm (330M parameters) is larger than xlm-roberta-base (279M parameters), by the parameter counts their publishers report.

Which is cheaper to run, deberta-v2-large-japanese-char-wwm or xlm-roberta-base?

At 4-bit, deberta-v2-large-japanese-char-wwm fits on 1x MI300X from $1.85 an hour and xlm-roberta-base on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use deberta-v2-large-japanese-char-wwm commercially?

Yes. deberta-v2-large-japanese-char-wwm is released under Creative Commons Attribution-ShareAlike 4.0. CC BY-SA 4.0 permits sharing and adapting, including commercially, with credit to the creator, and requires adaptations to be released under the same license.

Can I use xlm-roberta-base commercially?

Yes. xlm-roberta-base 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.

Related Comparisons