# ko-sroberta-multitask vs nomic-embed-text-v1: Specs and GPU Cost Source: https://savrn.com/models/compare/ko-sroberta-multitask-vs-nomic-embed-text-v1 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- | Field | [ko-sroberta-multitask](https://savrn.com/models/ko-sroberta-multitask) jhgan/ko-sroberta-multitask | [nomic-embed-text-v1](https://savrn.com/models/nomic-embed-text-v1) nomic-ai/nomic-embed-text-v1 | | --- | --- | --- | | Publisher | Junghyun Gan | Nomic AI | | Task | Sentence similarity | Sentence similarity | | Modality | Text | Text | | Parameters, as reported | 111M parameters | 137M parameters | | Architecture | RobertaModel | NomicBertModel | | Library | sentence-transformers | sentence-transformers | | Context length | 514 tokens | 8,192 tokens | | Repository size | 2.5 GB | 1.8 GB | | Artifact formats | safetensors, onnx, openvino, pytorch, tf | safetensors, onnx, pytorch | | 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 | 3ac47f125a41 | | Downloads reported by the hub | 590.6k | 1.5M | | Last observed | 2026-09-18 | 2026-10-24 | 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. ### nomic-embed-text-v1 | Benchmark | Conditions | Result | Reported by | Revision | Date | | --- | --- | --- | --- | --- | --- | | MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 76.8507 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric apComparison conditions not established | 40.5922 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 71.0163 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric accuracyComparison conditions not established | 91.5189 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric apComparison conditions not established | 88.5035 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric f1Comparison conditions not established | 91.5034 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 47.364 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 46.7271 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1Comparison conditions not established | 25.178 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_10Comparison conditions not established | 40.244 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_100Comparison conditions not established | 41.322 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1000Comparison conditions not established | 41.331 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_3Comparison conditions not established | 35.017 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_5Comparison conditions not established | 37.99 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1Comparison conditions not established | 25.605 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_10Comparison conditions not established | 40.422 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_100Comparison conditions not established | 41.507 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1000Comparison conditions not established | 41.516 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_3Comparison conditions not established | 35.23 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_5Comparison conditions not established | 38.15 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1Comparison conditions not established | 25.178 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_10Comparison conditions not established | 49.258 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_100Comparison conditions not established | 53.776 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1000Comparison conditions not established | 53.995 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_3Comparison conditions not established | 38.429 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_5Comparison conditions not established | 43.803 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1Comparison conditions not established | 25.178 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_10Comparison conditions not established | 7.831 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_100Comparison conditions not established | 0.979 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1000Comparison conditions not established | 0.1 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_3Comparison conditions not established | 16.121 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_5Comparison conditions not established | 12.29 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1Comparison conditions not established | 25.178 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_10Comparison conditions not established | 78.307 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_100Comparison conditions not established | 97.866 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1000Comparison conditions not established | 99.573 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_3Comparison conditions not established | 48.364 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_5Comparison conditions not established | 61.451 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArxivClusteringP2P | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 45.9303 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | | MTEB ArxivClusteringS2S | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 36.6458 | [nomic-ai](https://huggingface.co/nomic-ai/nomic-embed-text-v1) Publisher reported | Evaluated revision not stated | — | ## 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 Research, 2026-09-18 ## SAVRN's Notes on nomic-embed-text-v1 For an embedding model the memory line is beside the point: 0.3 GB at 16-bit against one MI300X with 192 GB, the cheapest listed setup at $1.85 an hour. Nobody reserves that card for one copy of a 137M parameter encoder; vectors per hour, not fit, is the number to measure. The 8,192 token window is the reason to choose it over a shorter encoder: a whole contract goes in as one vector, not a stack of fragments. Check the prefix rule first: the publisher's card requires a task instruction on every input, one form for the documents you store and another for the queries you ask, and a pipeline that omits them is not running the model as published. Apache 2.0 then lets you embed customer data commercially and ship a fine-tuned copy with the notices kept. Weights updated April 7, 2026, in safetensors, onnx and pytorch. SAVRN Research, 2026-09-18 ## Questions ### Which is larger, ko-sroberta-multitask or nomic-embed-text-v1? nomic-embed-text-v1 (137M 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 nomic-embed-text-v1? At 4-bit, ko-sroberta-multitask fits on 1x MI300X from $1.85 an hour and nomic-embed-text-v1 on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use nomic-embed-text-v1 commercially? Yes. nomic-embed-text-v1 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 - [ko-sroberta-multitask vs multilingual-e5-small](https://savrn.com/models/compare/ko-sroberta-multitask-vs-multilingual-e5-small) - [ko-sroberta-multitask vs paraphrase-multilingual-MiniLM-L12-v2](https://savrn.com/models/compare/ko-sroberta-multitask-vs-paraphrase-multilingual-minilm-l12-v2) - [distiluse-base-multilingual-cased-v1 vs nomic-embed-text-v1](https://savrn.com/models/compare/distiluse-base-multilingual-cased-v1-vs-nomic-embed-text-v1) - [distiluse-base-multilingual-cased-v2 vs nomic-embed-text-v1](https://savrn.com/models/compare/distiluse-base-multilingual-cased-v2-vs-nomic-embed-text-v1)