# jina-reranker-v2-base-multilingual by Jina AI: Open Model Source: https://savrn.com/models/jina-reranker-v2-base-multilingual Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve jina-reranker-v2-base-multilingual (278M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.6 GB | 0.7 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.3 GB | 0.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.1 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 25, 2026. [jina-reranker-v2-base-multilingual on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/jina-reranker-v2-base-multilingual/gpus) ## SAVRN's Notes on jina-reranker-v2-base-multilingual Read the license before the spec sheet on this one. jina-reranker-v2-base-multilingual ships under CC BY-NC 4.0, which allows sharing and adapting with credit for non-commercial purposes only; commercial use needs separate permission from the rights holder. Hardware is the easy part. A 278M parameter cross-encoder on XLMRobertaForSequenceClassification needs 0.7 GB at 16-bit, and the cheapest Index listing that holds it is one MI300X with 192 GB at $1.85 an hour, so co-locate it with the embedding and generation models it sits between. It takes a query and document pair and returns a relevance score, the step between vector search and answer generation. The pair has to fit in 1,026 tokens, so long passages need trimming. Access is open, the 24 files total 5.3 GB across safetensors, ONNX and PyTorch copies, and the last update was October 21, 2025. For a commercial product, get that permission in writing first. SAVRN Research, 2026-09-18 ## Model Card The Jina Reranker v2 (jina-reranker-v2-base-multilingual) is a transformer-based model that has been fine-tuned for text reranking task, which is a crucial component in many information retrieval systems. It is a cross-encoder model that takes a query and a document pair as input and outputs a score indicating the relevance of the document to the query. The model is trained on a large dataset of query-document pairs and is capable of reranking documents in multiple languages with high accuracy. Compared with the state-of-the-art reranker models, including the previous released jina-reranker-v1-base-en, the Jina Reranker v2 model has demonstrated competitiveness across a series of benchmarks… Excerpt from the card by Jina AI, licensed cc-by-nc-4.0. ## Configuration Architecture XLMRobertaForSequenceClassification Context length (tokens) 1,026 Layers 12 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Vocabulary size 250,002 Stored precision bfloat16 ## Identity and Version Repository jinaai/jina-reranker-v2-base-multilingual Publisher Jina AI Task Text ranking Modality Other Library transformers Parameters 278M parameters Languages Not stated by the source Revision 9cfeff2df7d40d1b78e75e5e9cebec92a99813c9 First published 2024-06-19 Last updated 2025-10-21 ## Files and Weights 24 files, 5.3 GB in total. The weights are 9 files totalling 5.3 GB in bin, onnx, safetensors. Weights9 files · 5.3 GB Configuration10 files · 118.6 KB Tokenizer2 files · 17.1 MB Documentation1 file · 15.7 KB Repository2 files · 4.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 556.9 MB | ab2595ab9f34 | | onnx/model.onnx | Weights | 1.1 GB | 0ef3f7978f7b | | onnx/model_bnb4.onnx | Weights | 822.1 MB | df70759eb3eb | | onnx/model_fp16.onnx | Weights | 557.2 MB | 4ad94bcc1d73 | | onnx/model_int8.onnx | Weights | 279.6 MB | c5220cf8fe02 | | onnx/model_q4.onnx | Weights | 827.4 MB | a3744ee702ad | | onnx/model_quantized.onnx | Weights | 279.6 MB | c5220cf8fe02 | | onnx/model_uint8.onnx | Weights | 279.6 MB | 9498f606988b | | pytorch_model.bin | Weights | 561.6 MB | 318b11c3ce6d | | block.py | Configuration | 19.7 KB | — | | config.json | Configuration | 1.1 KB | — | | configuration_xlm_roberta.py | Configuration | 2.7 KB | — | | embedding.py | Configuration | 2.6 KB | — | | mha.py | Configuration | 28.0 KB | — | | mlp.py | Configuration | 6.2 KB | — | | modeling_xlm_roberta.py | Configuration | 43.8 KB | — | | special_tokens_map.json | Configuration | 964 B | — | | stochastic_depth.py | Configuration | 3.8 KB | — | | xlm_padding.py | Configuration | 9.8 KB | — | | README.md | Documentation | 15.7 KB | — | | .gitattributes | Repository | 1.6 KB | — | | .gitignore | Repository | 3.1 KB | — | | tokenizer.json | Tokenizer | 17.1 MB | 3a56def25aa4 | | tokenizer_config.json | Tokenizer | 1.1 KB | — | ## License and Download License cc-by-nc-4.0 Access Open weights, no gate Download size 5.3 GB [Download from Jina AI](https://huggingface.co/jinaai/jina-reranker-v2-base-multilingual) Released by Jina AI through its official repository on Hugging Face. [Read the license](https://creativecommons.org/licenses/by-nc/4.0/). ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 5.3 GB | | 16-bit | 0.6 GB | | 8-bit | 0.3 GB | | 4-bit | 0.1 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About jina-reranker-v2-base-multilingual ### How much GPU memory does jina-reranker-v2-base-multilingual need? About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (278M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run jina-reranker-v2-base-multilingual on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use jina-reranker-v2-base-multilingual commercially? Not without separate permission. jina-reranker-v2-base-multilingual is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder. ### What is jina-reranker-v2-base-multilingual's context length? 1,026 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text ranking ### [KielEmbed-Rerank](https://savrn.com/models/kielembed-rerank) [Tech](https://savrn.com/model-publishers/kiel2) This is a Cross Encoder model finetuned from BAAI/bge-reranker-base using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search. First install the Sentence Transformers library: Then you can load this model and run inference. Approximate statistics based on the first 100 samples: - perdevicetrainbatchsize: 4 - numtrainepochs: 1 - learningrate: 2e-05 - warmupsteps: 0.1 - gradientaccumulationsteps: 8 - fp16: True - perdevicetrainbatchsize: 4 - numtrainepochs: 1 - maxsteps: -1 - learningrate: 2e-05 - lrschedulertype: linear - lrschedulerkwargs: None - warmupsteps: 0.1 - optim: adamwtorchfused - optimargs: None… Open weights 278M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/kielembed-rerank) Model · Text ranking ### [GemmaDecision-270M](https://savrn.com/models/gemmadecision-270m) [Rajan Shukla](https://savrn.com/model-publishers/rajan2k) A fully tuned Gemma-270M candidate ranker: it scores each supplied choice together with the request, using a scalar decision head. Intended research tasks are banking-support topic selection and three-way evidence relations. It does not generate answers. The complete modified encoder and head are included. On the private fresh-prompt test, accuracy is 96.50% for four-way banking topics and 78.00% for three-way NLI, with an equal-family mean of 87.25%. Both frozen task targets were met on this private test. See RESULTS.md for both baselines, paired uncertainty, coverage, synthetic challenge results and failures. Package 0.2.0 uses ONNX Runtime on CPU by default. The standard install requires… Open weights gemma 268M parameters 32,768 tokens pytorch [View model](https://savrn.com/models/gemmadecision-270m) Model · Text ranking ### [cross-encoder-russian-msmarco](https://savrn.com/models/cross-encoder-russian-msmarco) [Dmitry Tishencko](https://savrn.com/model-publishers/dity) This is a sentence-transformers model based on a pre-trained DeepPavlov/rubert-base-cased and finetuned with MS-MARCO Russian passage ranking dataset. The model can be used for Information Retrieval in the Russian language: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you need to get the logits from the… Open weights mit 178M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/cross-encoder-russian-msmarco) Model · Text ranking ### [gte-reranker-modernbert-base](https://savrn.com/models/gte-reranker-modernbert-base) [Alibaba-NLP](https://savrn.com/model-publishers/alibaba-nlp) We are excited to introduce the gte-modernbert series of models, which are built upon the latest modernBERT pre-trained encoder-only foundation models. The gte-modernbert series models include both text embedding models and rerank models. The gte-modernbert models demonstrates competitive performance in several text embedding and text retrieval evaluation tasks when compared to similar-scale models from the current open-source community. This includes assessments such as MTEB, LoCO, and COIR evaluation. Use with transformers Use with sentence-transformers: Before you start, install the sentence-transformers libraries: Use with transformers.js Additionally, you can also deploy… Open weights apache-2.0 150M parameters 8,192 tokens transformers [View model](https://savrn.com/models/gte-reranker-modernbert-base) Model · Text ranking ### [mmarco-mMiniLMv2-L12-H384-v1](https://savrn.com/models/mmarco-mminilmv2-l12-h384-v1) [Sentence Transformers - Cross-Encoders](https://savrn.com/model-publishers/cross-encoder) This model was trained on the MMARCO dataset. It is a machine translated version of MS MARCO using Google Translate. It was translated to 14 languages. In our experiments, we observed that it performs also well for other languages. As a base model, we used the multilingual MiniLMv2 model. The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. The training code is available here: SBERT.net Training MS Marco The usage becomes easy when you have SentenceTransformers installed. Then, you can use the pre-trained… Open weights apache-2.0 118M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/mmarco-mminilmv2-l12-h384-v1) Model · Text ranking ### [ms-marco-electra-base](https://savrn.com/models/ms-marco-electra-base) [Sentence Transformers - Cross-Encoders](https://savrn.com/model-publishers/cross-encoder) This model was trained on the MS Marco Passage Ranking task. The model can be used for Information Retrieval: Given a query, encode the query will all possible passages (e.g. retrieved with ElasticSearch). Then sort the passages in a decreasing order. See SBERT.net Retrieve & Re-rank for more details. The training code is available here: SBERT.net Training MS Marco The usage is easy when you have SentenceTransformers installed. Then you can use the pre-trained models like this: In the following table, we provide various pre-trained Cross-Encoders together with their performance on the TREC Deep Learning 2019 and the MS Marco Passage Reranking dataset. Open weights apache-2.0 109M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/ms-marco-electra-base) ## Jina AI [All models and datasets](https://savrn.com/model-publishers/jinaai) ## Versions - [9cfeff2df7d4](https://savrn.com/models/jina-reranker-v2-base-multilingual/versions/9cfeff2df7d4) · current 2026-10-25 ## Explore More - [All text ranking models](https://savrn.com/models/tasks/text-ranking) - [All models under cc-by-nc-4.0](https://savrn.com/models/licenses/cc-by-nc-4-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-19. - [Jina AI website](https://jina.ai/models/) - [Hugging Face record](https://huggingface.co/jinaai/jina-reranker-v2-base-multilingual) - [How the hub is built](https://savrn.com/model-hub/methodology)