# esm2_t33_650M_UR50D vs xlm-roberta-large: Specs and GPU Cost Source: https://savrn.com/models/compare/esm2-t33-650m-ur50d-vs-xlm-roberta-large Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- | Field | [esm2_t33_650M_UR50D](https://savrn.com/models/esm2-t33-650m-ur50d) facebook/esm2_t33_650M_UR50D | [xlm-roberta-large](https://savrn.com/models/xlm-roberta-large) FacebookAI/xlm-roberta-large | | --- | --- | --- | | Publisher | AI at Meta | Facebook AI community | | Task | Fill mask | Fill mask | | Modality | Text | Text | | Parameters, as reported | 652M parameters | 561M parameters | | Architecture | EsmForMaskedLM | XLMRobertaForMaskedLM | | Library | transformers | transformers | | Context length | 1,026 tokens | 514 tokens | | Repository size | 7.8 GB | 11.2 GB | | Artifact formats | safetensors, pytorch, tf | safetensors, onnx, pytorch, jax, tf | | License | mit | mit | | Access | Open weights, no gate | Open weights, no gate | | Memory at 16-bit (weights and margin) | 1.6 GB | 1.3 GB | | Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 | | Memory at 4-bit (weights and margin) | 0.4 GB | 0.3 GB | | Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 | | Revision viewed | 08e4846e5371 | c23d21b0620b | | Downloads reported by the hub | 4.9M | 2.4M | | Last observed | 2026-10-22 | 2026-10-22 | 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 esm2_t33_650M_UR50D A protein language model from AI at Meta, built for teams fine-tuning on sequence data: 652M parameters, a 1,026-token window, and a run cost of 1.6 GB at 16-bit, 0.8 GB at 8-bit, 0.4 GB at 4-bit — under one percent of the cheapest Index card at $1.85 an hour, so pack copies or fine-tuning jobs per GPU rather than dedicating one. The odd number is storage: 7.8 GB across nine files, because the repo ships float32 weights in safetensors, pytorch and tf formats. Pull one. MIT permits commercial use, modification and redistribution with the notice kept, so a fine-tuned variant can ship to customers. The 1,026-token cap is a real constraint on long proteins — plan chunking or a larger ESM2 rung before committing. Files date to March 2023 and have not moved since; no host prices it per token, and at this size none should. SAVRN Research ## SAVRN's Notes on xlm-roberta-large Fitting this one is never the problem. At 16-bit the weights are 1.1 GB and the run needs 1.3 GB, so the cheapest setup on the page, one 192 GB MI300X at $1.85 an hour on-demand, has room for more than a hundred copies; put it on a GPU already serving something else. What the footprint buys is a fill-mask model trained on 2.5 TB of filtered CommonCrawl in 100 languages with a 250,002-entry vocabulary: a starting layer for multilingual text work you tune yourself, not a finished application. MIT asks only that the copyright and permission notice travel with what you ship; commercial use, modification and redistribution are allowed. Note the 514-token context, sentences and short passages rather than documents, and the 17 files totaling 11.2 GB across five formats, of which your runtime needs one. The releasing team did not write the card; start from arXiv 1911.02116. SAVRN Research, 2026-09-18 ## Questions ### Which is larger, esm2_t33_650M_UR50D or xlm-roberta-large? esm2_t33_650M_UR50D (652M parameters) is larger than xlm-roberta-large (561M parameters), by the parameter counts their publishers report. ### Which is cheaper to run, esm2_t33_650M_UR50D or xlm-roberta-large? At 4-bit, esm2_t33_650M_UR50D fits on 1x MI300X from $1.85 an hour and xlm-roberta-large on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use esm2_t33_650M_UR50D commercially? Yes. esm2_t33_650M_UR50D 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. ### Can I use xlm-roberta-large commercially? Yes. xlm-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. ## Related Comparisons - [bert-large-uncased vs xlm-roberta-large](https://savrn.com/models/compare/bert-large-uncased-vs-xlm-roberta-large) - [ModernBERT-large vs xlm-roberta-large](https://savrn.com/models/compare/modernbert-large-vs-xlm-roberta-large)