Model reference · open weights

ettin-reranker

ettin-reranker is an open-weight embedding model from cross-encoder, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings cross-encoder 3 variants 17k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What ettin-reranker is

ettin-reranker-68m-v1 This is a Cross Encoder model finetuned from jhu-clsp/ettin-encoder-68m on the cross-encoder/ettin-reranker-v1-data dataset using the sentence-transformers library. It computes scores for pairs of texts, which can be used for text reranking and semantic search. See the release blogpost for details on the training recipe, evaluation results, and speed benchmarks against other public rerankers. The Evaluation section below also has the headline numbers. Model Details Model Description - Model Type: Cross Encoder - Base model: jhu-clsp/ettin-encoder-68m <!-- at revision ac19ae4bc51093b31c475665ac872a936d056cc2 -- - Maximum Sequence Length: 7999 tokens - Number of Output Labels: 1 label - Supported Modality: Text - Training Dataset: cross-encoder/ettin-reranker-v1-data - Language: en - License: apache-2.0 Model Sources - Documentation: Sentence Transformers Documentation - Documentation: Cross Encoder Documentation - Repository: Sentence Transformers on GitHub - Hugging Face: Cross Encoders on Hugging Face Full Model Architecture Usage Direct Usage (Sentence Transformers) First install the Sentence Transformers library: Then you can load this model and run inference. Direct Usage (Transformers) -- Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. -- Out-of-Scope Use List how the model may foreseeably be misused and address what users ought not to do with the model. -- Evaluation MTEB(eng, v2) Retrieval Each model in the ettin-reranker-v1 family was evaluated on the full MTEB(eng, v2) Retrieval benchmark (10 tasks, top-100 reranked) using MTEB's two-stage reranking flow, pairing each reranker with six embedding models that span the speed/quality spectrum. The dashed retriever-only line in each chart below is the headline number to beat. Anything below it means the reranker actively hurts the pipeline on average: Mean NDCG@10 over the 6 embedder pairings, sorted by MTEB. The released ettin-reranker-v1 family is in bold, and the teacher mixedbread-ai/mxbai-rerank-large-v2 is <uunderlined</u. See the release blogpost for the full analysis and per-model commentary. Speed All six released models were benchmarke

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makercross-encoder
TypeEmbedding models
Parameters (lead)68M
Context7,999 tokens
Variants3
Runs withsentence-transformers
Based onjhu-clsp/ettin-encoder-68m
Released2026-05-15
Popularity17k downloads / month
Likes5
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
ettin-reranker-68m-v168MBF16~0.2 GBWeights ↗
ettin-reranker-32m-v132MBF16~0.1 GBWeights ↗
ettin-reranker-400m-v1395MBF16~0.9 GBWeights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Cross Encoder RerankingNanoMSMARCO R100Map0.617
Cross Encoder RerankingNanoMSMARCO R100Mrr@100.613
Cross Encoder RerankingNanoMSMARCO R100Ndcg@100.683
Cross Encoder RerankingNanoNFCorpus R100Map0.372
Cross Encoder RerankingNanoNFCorpus R100Mrr@100.562
Cross Encoder RerankingNanoNFCorpus R100Ndcg@100.407
Cross Encoder RerankingNanoNQ R100Map0.722
Cross Encoder RerankingNanoNQ R100Mrr@100.753
Cross Encoder RerankingNanoNQ R100Ndcg@100.775
Cross Encoder RerankingNanoFiQA2018 R100Map0.538
Cross Encoder RerankingNanoFiQA2018 R100Mrr@100.652
Cross Encoder RerankingNanoFiQA2018 R100Ndcg@100.591
Cross Encoder RerankingNanoTouche2020 R100Map0.477
Cross Encoder RerankingNanoTouche2020 R100Mrr@100.826
Cross Encoder RerankingNanoTouche2020 R100Ndcg@100.563
Cross Encoder RerankingNanoSciFact R100Map0.702
Cross Encoder RerankingNanoSciFact R100Mrr@100.7
Cross Encoder RerankingNanoSciFact R100Ndcg@100.746
Cross Encoder RerankingNanoHotpotQA R100Map0.932
Cross Encoder RerankingNanoHotpotQA R100Mrr@100.99
Cross Encoder RerankingNanoHotpotQA R100Ndcg@100.958
Cross Encoder RerankingNanoArguAna R100Map0.574
Cross Encoder RerankingNanoArguAna R100Mrr@100.575
Cross Encoder RerankingNanoArguAna R100Ndcg@100.688

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys ettin-reranker for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (ettin-reranker below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"ettin-reranker","input":"text to embed"}'

Details

Languages, data & research

Languages

en

Tags

sentence-transformers onnx safetensors openvino modernbert cross-encoder reranker generated_from_trainer dataset_size:143393475 loss:MSELoss text-ranking en model-index text-embeddings-inference

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want ettin-reranker on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms