SAVRN Model Hub · Comparisons
ko-sroberta-multitask vs paraphrase-multilingual-MiniLM-L12-v2
Ko-sroberta-multitask has 111M parameters and paraphrase-multilingual-MiniLM-L12-v2 has 118M parameters; at 16-bit, ko-sroberta-multitask needs about 0.3 GB (1x MI300X from $1.85 an hour) and paraphrase-multilingual-MiniLM-L12-v2 about 0.3 GB (1x MI300X from $1.85 an hour).
| Field | ko-sroberta-multitask jhgan/ko-sroberta-multitask | paraphrase-multilingual-MiniLM-L12-v2 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 |
|---|---|---|
| Publisher | Junghyun Gan | Sentence Transformers |
| Task | Sentence similarity | Sentence similarity |
| Modality | Text | Text |
| Parameters, as reported | 111M parameters | 118M parameters |
| Architecture | RobertaModel | BertModel |
| Library | sentence-transformers | sentence-transformers |
| Context length | 514 tokens | 512 tokens |
| Repository size | 2.5 GB | 4.6 GB |
| Artifact formats | safetensors, onnx, openvino, pytorch, tf | safetensors, onnx, openvino, pytorch, tf |
| License | Not stated | 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 | 8fca7c9c98c2 | e8f8c211226b |
| Downloads reported by the hub | 590.6k | 45.7M |
| 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 ko-sroberta-multitask
Korean sentence embeddings are the job here. Junghyun Gan trained this 111M parameter RoBERTa on the KorSTS and KorNLI sets in a multi-task run, and it turns a sentence or paragraph into a 768-dimensional vector for clustering or semantic search. At 16-bit the weights are 0.2 GB and the run needs 0.3 GB, so hardware is not the decision. The cheapest Index slot, one MI300X with 192 GB at $1.85 an hour on demand, leaves nearly the whole card idle; put it beside a larger model on a box you already run.
The license field is blank, and that is the first thing we would settle with the publisher before a paid deployment. Context is 514 tokens, so it encodes passages, not documents. The 2.5 GB download across 21 files is the weights shipped in five formats, safetensors, ONNX, OpenVINO, PyTorch and TF, which opens a CPU-side serving path.
SAVRN's Notes on paraphrase-multilingual-MiniLM-L12-v2
Every sentence or paragraph you feed this comes back as 384 numbers, a dense vector you can cluster or search against. The vocabulary runs to 250,037 entries and the name says multilingual, so one index can hold more than one language. Memory is not a decision here: 0.3 GB at 16-bit on the cheapest card we track, a 192 GB MI300X at $1.85 an hour, so it shares a card rather than owning one.
Check the 512-token ceiling first: anything longer gets chunked before it is embedded. The last update landed on 2026-01-28, so pin the revision your pipeline was built against. Without the sentence-transformers library you run the transformer and apply the pooling step yourself. Apache 2.0 permits commercial use, modification and redistribution; keep the notices, note significant changes, and the patent grant from contributors comes with it.
Questions
Which is larger, ko-sroberta-multitask or paraphrase-multilingual-MiniLM-L12-v2?
paraphrase-multilingual-MiniLM-L12-v2 (118M parameters) is larger than ko-sroberta-multitask (111M parameters), by the parameter counts their publishers report.
Which is cheaper to run, ko-sroberta-multitask or paraphrase-multilingual-MiniLM-L12-v2?
At 4-bit, ko-sroberta-multitask fits on 1x MI300X from $1.85 an hour and paraphrase-multilingual-MiniLM-L12-v2 on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use paraphrase-multilingual-MiniLM-L12-v2 commercially?
Yes. paraphrase-multilingual-MiniLM-L12-v2 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.