Up to date
sentence-transformers Apache 2.0 out 5 years ago
109M parameters, text in, embeddings out, 514 tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #45 in Embeddings · score 90.1 method v1 Sources 3 Downloads 30d 1.3M · #94 of 619 tracked
Picked by rule from 4 tracked pieces: the lab's own post, the most shared, a field report, the latest.
all-mpnet-base-v2 and paraphrase-mpnet-base-v2 are both 109M parameter sentence similarity models released under Apache License 2.0.
The 1 pick above, plus these 3. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | HF Inference | — | — | — | — | Oct 25 |
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; 2 quantized builds for local use; a big base for builders (426 fine-tunes, adapters and merges).
Top Spaces running it: Gradio-Blocks/pubmed-abstract-retriever ♥ 14 · pritamdeka/health-article-keyphrase-generator ♥ 8 · pritamdeka/pubmed-abstract-retriever ♥ 6 · X-iZhang/RadEval ♥ 5
Weights only, an estimate: leave room for the KV cache. Method
About 0.1 GB at INT4, 0.1 GB at FP8, 0.3 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2022-03-02), amber triangles are 1 dated article (each links to it), grey ticks are repo commits.
428 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
It maps sentences and paragraphs to a 768 dimensional dense vector space for tasks like clustering or semantic search.[1]
Generated 2026-10-07 15:04 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in Embeddings
| Pipeline tag | sentence-similarity |
|---|---|
| Library | sentence-transformers |
| Architectures | MPNetModel |
| Model type | mpnet |
| Params by dtype | F32: 109,486,464 · I64: 514 |
| Size band | S |
| MoE | no |
| Context length | 514 (config.json max_position_embeddings) |
| Papers | arXiv:1908.10084 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
vLLM: not in registry · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: not in registry · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for paraphrase-mpnet-base-v2: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.3 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 0.1 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.1 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
finetune: 426quantized: 2
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| nikcheerla/amd-partial-v1 | finetune | — | 109M | S | — | nikcheerla | 0 | 81.6k |
| nikcheerla/amd-partial-phonetree-v1 | finetune | — | 109M | S | — | nikcheerla | 0 | 81.1k |
| nikcheerla/amd-full-phonetree-v1 | finetune | — | 109M | S | — | nikcheerla | 0 | 80.2k |
| onyx-dot-app/information-content-model | finetune | — | 109M | S | — | onyx-dot-app | 0 | 41.9k |
| kasraarabi/finetuned-caption-embedding | finetune | — | 109M | S | — | kasraarabi | 0 | 10.9k |
| waterabbit114/my-setfit-classifier_toxic | finetune | — | 109M | S | — | waterabbit114 | 0 | 9.7k |
| tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-aspect | finetune | — | 109M | S | — | tomaarsen | 1 | 6.7k |
| tomaarsen/setfit-absa-paraphrase-mpnet-base-v2-restaurants-polarity | finetune | — | 109M | S | — | tomaarsen | 0 | 6.1k |
| praisethefool/human_tech-fields-multilabelclassifier | finetune | — | 109M | S | — | praisethefool | 0 | 2.6k |
| Xenova/paraphrase-mpnet-base-v2 | quantized | — | — | — | — | Xenova | 0 | 2.5k |
| KhoaUSA76/contrastive-sensitive-classification | finetune | — | 109M | S | — | KhoaUSA76 | 0 | 1.5k |
| RagN/ABSA-aspect | finetune | — | 109M | S | — | RagN | 0 | 1.1k |
| WeksteinEyal/setfit-model | finetune | — | 109M | S | — | WeksteinEyal | 0 | 1.1k |
| tomaarsen/setfit-paraphrase-mpnet-base-v2-sst2-8-shot | finetune | — | — | — | apache-2.0 | tomaarsen | 4 | 920 |
| RagN/ABSA-polarity | finetune | — | 109M | S | — | RagN | 0 | 1.1k |
| Shankhdhar/classifier_woog | finetune | — | 109M | S | — | Shankhdhar | 0 | 891 |
| andreacristiano/stancedetection | finetune | — | 109M | S | — | andreacristiano | 0 | 835 |
| joshuasundance/mtg-coloridentity-multilabel-classification | finetune | — | 109M | S | mit | joshuasundance | 4 | 467 |
| dendimaki/few-shots-apeiron-model-v2 | finetune | — | 109M | S | — | dendimaki | 0 | 596 |
| ennygaebs/cv-job-matcher | finetune | — | 109M | S | — | ennygaebs | 1 | 544 |
| Davide1999/setfit-absa-paraphrase-mpnet-base-v2-restaurants-aspect | finetune | — | 109M | S | — | Davide1999 | 1 | 495 |
| waterabbit114/my-setfit-classifier_threat | finetune | — | 109M | S | — | waterabbit114 | 0 | 426 |
| dnth/setfit-riasec-classifier-subset | finetune | — | 109M | S | — | dnth | 1 | 325 |
| Shankhdhar/classifier_woog_botnal | finetune | — | 109M | S | — | Shankhdhar | 0 | 373 |
| Gurveer05/paraphrase-mpnet-eedi-2024 | finetune | — | 109M | S | — | Gurveer05 | 0 | 306 |
| tushifire/setfit-break_task | finetune | — | 109M | S | — | tushifire | 0 | 300 |
| frankmorales2020/my-awesome-setfit-model | finetune | — | 109M | S | — | frankmorales2020 | 1 | 244 |
| harshita23sh/setfit-model-intent-classification-insurance | finetune | — | 109M | S | — | harshita23sh | 0 | 276 |
| ennygaebs/cv-jd-matcher | finetune | — | 109M | S | — | ennygaebs | 0 | 252 |
| ardi555/setfit-SentEval-classification | finetune | — | 109M | S | — | ardi555 | 0 | 250 |
| Shankhdhar/classifier_woog_shoegr | finetune | — | 109M | S | — | Shankhdhar | 0 | 242 |
| Andyrasika/setfit-absa-paraphrase-mpnet-base-v2-restaurants-polarity | finetune | — | 109M | S | — | Andyrasika | 0 | 241 |
| vidhi0206/setfit-paraphrase-mpnet-ag_news | finetune | — | 109M | S | — | vidhi0206 | 0 | 241 |
| CrisisNarratives/setfit-13classes-single_label | finetune | — | 109M | S | mit | CrisisNarratives | 0 | 239 |
| dendimaki/emotionSample | finetune | — | 109M | S | — | dendimaki | 0 | 239 |
| dappradar/setfit-model | finetune | — | 109M | S | — | dappradar | 0 | 238 |
| NazmusAshrafi/setfit-absa-sm-stock-tweet-aspect | finetune | — | 109M | S | — | NazmusAshrafi | 0 | 232 |
| bhaskars113/guinness-segments-model | finetune | — | 109M | S | — | bhaskars113 | 0 | 229 |
| HelgeKn/SemEval-multi-class-10 | finetune | — | 109M | S | — | HelgeKn | 0 | 226 |
| CrisisNarratives/setfit-8classes-multi_label | finetune | — | 109M | S | mit | CrisisNarratives | 0 | 226 |
| Date | Commit | SHA |
|---|---|---|
| 2025-08-19 | Add `text-embeddings-inference` tag & snippet (#4) | 6cc9279 |
| 2025-03-06 | Remove deprecated (SEB) evaluation results section | 0446e4e |
| 2024-11-05 | Add exported openvino model 'openvino_model_qint8_quantized.xml' | bef3689 |
| 2024-10-11 | Add new SentenceTransformer model with an openvino backend | ae400ae |
| 2024-10-11 | Add new SentenceTransformer model with an openvino backend | b240cf2 |
| 2024-10-11 | Add exported ONNX model 'model_qint8_avx512_vnni.onnx' | 64b859d |
| 2024-10-11 | Add exported ONNX model 'model_qint8_avx512.onnx' | ed72c70 |
| 2024-10-11 | Add exported ONNX model 'model_quint8_avx2.onnx' | f206c57 |
| 2024-10-11 | Add exported ONNX model 'model_qint8_arm64.onnx' | 7b92280 |
| 2024-10-11 | Add exported ONNX model 'model_O4.onnx' | 4f812b7 |
| 2024-10-11 | Add exported ONNX model 'model_O3.onnx' | 741a18a |
| 2024-10-11 | Add exported ONNX model 'model_O2.onnx' | d7f84c3 |
| 2024-10-11 | Add exported ONNX model 'model_O1.onnx' | bc01eae |
| 2024-10-11 | Add new SentenceTransformer model with an onnx backend | 96c9e3b |
| 2024-03-07 | Adding `safetensors` variant of this model (#2) | e6981e5 |
| 2024-02-12 | Update Sentence Transformers metadata (#1) | 3a19695 |
| 2022-06-15 | Add TF weights | 18df4b2 |
| 2021-08-31 | up | 505b5e8 |
| 2021-08-05 | Update README.md | b2b82f2 |
| 2021-06-22 | Add new SentenceTransformer model. | a867aef |
| 2021-05-20 | upload | 0ddf2eb |
| 2021-05-20 | initial commit | e292aca |
Hosted endpoints observed for paraphrase-mpnet-base-v2, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| HF Inference hf | sentence-transformers/paraphrase-mpnet-base-v2 | — | — | — | — | — | — | — | live | 2026-10-25 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:36 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:04 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
