# indonesian-roberta-base-posp-tagger vs Source: https://savrn.com/models/compare/indonesian-roberta-base-posp-tagger-vs-openmed-ner-dnadetect-supermedical-125m Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- | Field | [indonesian-roberta-base-posp-tagger](https://savrn.com/models/indonesian-roberta-base-posp-tagger) w11wo/indonesian-roberta-base-posp-tagger | [OpenMed-NER-DNADetect-SuperMedical-125M](https://savrn.com/models/openmed-ner-dnadetect-supermedical-125m) OpenMed/OpenMed-NER-DNADetect-SuperMedical-125M | | --- | --- | --- | | Publisher | Wilson Wongso | OpenMed | | Task | Token classification | Token classification | | Modality | Text | Text | | Parameters, as reported | 124M parameters | 124M parameters | | Architecture | RobertaForTokenClassification | RobertaForTokenClassification | | Library | transformers | transformers | | Context length | 514 tokens | 514 tokens | | Repository size | 1.5 GB | 253.5 MB | | Artifact formats | safetensors, pytorch, tensorboard, tf | safetensors | | License | mit | apache-2.0 | | Access | Open weights, no gate | Open weights, no gate | | Memory at 16-bit (weights and margin) | 0.3 GB | 0.3 GB | | Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 | | Memory at 4-bit (weights and margin) | 0.1 GB | 0.1 GB | | Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 | | Revision viewed | 506779636093 | 2c0f34199a82 | | Downloads reported by the hub | 3.4M | 199.4k | | Last observed | 2026-10-23 | 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. ## Other Reported Results These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it. ### indonesian-roberta-base-posp-tagger | Benchmark | Conditions | Result | Reported by | Revision | Date | | --- | --- | --- | --- | --- | --- | | indonlu | Configuration pospTask Token ClassificationMetric AccuracyComparison conditions not established | 0.96251 | [w11wo](https://huggingface.co/w11wo/indonesian-roberta-base-posp-tagger) Publisher reported | Evaluated revision not stated | — | | indonlu | Configuration pospTask Token ClassificationMetric F1Comparison conditions not established | 0.96251 | [w11wo](https://huggingface.co/w11wo/indonesian-roberta-base-posp-tagger) Publisher reported | Evaluated revision not stated | — | | indonlu | Configuration pospTask Token ClassificationMetric PrecisionComparison conditions not established | 0.96251 | [w11wo](https://huggingface.co/w11wo/indonesian-roberta-base-posp-tagger) Publisher reported | Evaluated revision not stated | — | | indonlu | Configuration pospTask Token ClassificationMetric RecallComparison conditions not established | 0.96251 | [w11wo](https://huggingface.co/w11wo/indonesian-roberta-base-posp-tagger) Publisher reported | Evaluated revision not stated | — | ## SAVRN's Notes on indonesian-roberta-base-posp-tagger This model tags Indonesian text with parts of speech. It is an Indonesian RoBERTa base, 124M parameters, fine-tuned on the IndoNLU benchmark, and it draws about 2.6 million downloads a month, which suggests it sits inside many automated pipelines. The MIT license allows commercial use. Part-of-speech tags are rarely the end product; they feed search, grammar tools and linguistic analysis. For those uses in Indonesian, this is a well-established, cheap component that runs on a CPU. SAVRN Research, 2026-09-18 ## SAVRN's Notes on OpenMed-NER-DNADetect-SuperMedical-125M This OpenMed model tags proteins, DNA, RNA, cell lines and cell types in biomedical text. It is a 124M-parameter RoBERTa model, small enough to annotate large literature collections on a CPU. Apache 2.0 allows commercial use. For literature mining in molecular biology, it is a useful first pass that turns abstracts into searchable entities. Check a sample of its output by hand; gene and protein names are notoriously ambiguous. SAVRN Research, 2026-09-18 ## Questions ### Which is larger, indonesian-roberta-base-posp-tagger or OpenMed-NER-DNADetect-SuperMedical-125M? indonesian-roberta-base-posp-tagger (124M parameters) is larger than OpenMed-NER-DNADetect-SuperMedical-125M (124M parameters), by the parameter counts their publishers report. ### Which is cheaper to run, indonesian-roberta-base-posp-tagger or OpenMed-NER-DNADetect-SuperMedical-125M? At 4-bit, indonesian-roberta-base-posp-tagger fits on 1x MI300X from $1.85 an hour and OpenMed-NER-DNADetect-SuperMedical-125M on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use indonesian-roberta-base-posp-tagger commercially? Yes. indonesian-roberta-base-posp-tagger 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 OpenMed-NER-DNADetect-SuperMedical-125M commercially? Yes. OpenMed-NER-DNADetect-SuperMedical-125M 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 - [indonesian-roberta-base-posp-tagger vs OpenMed-NER-PathologyDetect-TinyMed-135M](https://savrn.com/models/compare/indonesian-roberta-base-posp-tagger-vs-openmed-ner-pathologydetect-tinymed-135m) - [indonesian-roberta-base-posp-tagger vs span-marker-bert-base-uncased-acronyms](https://savrn.com/models/compare/indonesian-roberta-base-posp-tagger-vs-span-marker-bert-base-uncased-acronyms)