# mxbai-rerank-xsmall-v1 by Mixedbread: Open-Weight Model Source: https://savrn.com/models/mxbai-rerank-xsmall-v1 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve mxbai-rerank-xsmall-v1 (71M 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 | 0.1 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 | | 8-bit | 0.1 GB | 0.1 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 | 0.0 GB | 0.0 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. [mxbai-rerank-xsmall-v1 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/mxbai-rerank-xsmall-v1/gpus) ## SAVRN's Notes on mxbai-rerank-xsmall-v1 Rerankers earn their keep at the end of a retrieval pipeline, scoring what a first-pass search returned, and this one is the smallest in Mixedbread's family at 71M parameters. Memory at 16-bit is 0.2 GB with 0.1 GB of weights; at 4-bit both round to zero. The cheapest listed setup is a lone MI300X with 192 GB at $1.85 an hour on demand, so it shares a GPU with the embedding model and the generator. Under Apache 2.0 it can go into a commercial product, provided the license and copyright notices stay attached. Weigh the 512-token context against your chunk size; anything past that limit is not scored. Safetensors and ONNX are both in the 524 MB download. No base model, dataset or reported evaluations are listed, so quality claims come from your own test set. The publisher serves its large model through an API; this one you own outright. SAVRN Research, 2026-09-18 ## Model Card By Mixedbread, published under apache-2.0, revision b5c6e9da73ab. The crispy rerank family from [Mixedbread](https://mixedbread.com). Looking for a simple end-to-end retrieval solution? Meet Omni, our multimodal and multilingual model.[Get in touch for access.](https://mixedbread.com) ### mxbai-rerank-xsmall-v1 This is the smallest model in our family of powerful reranker models. You can learn more about the models in our [blog post](https://www.mixedbread.ai/blog/mxbai-rerank-v1). We have three models: - [mxbai-rerank-xsmall-v1](https://savrn.com/models/mxbai-rerank-xsmall-v1)() - [mxbai-rerank-base-v1](https://huggingface.co/mixedbread-ai/mxbai-rerank-base-v1) - [mxbai-rerank-large-v1](https://huggingface.co/mixedbread-ai/mxbai-rerank-large-v1) ### Quickstart Currently, the best way to use our models is with the most recent version of sentence-transformers. pip install -U sentence-transformers Let's say you have a query, and you want to rerank a set of documents. You can do that with only one line of code: [Read the full model card (1,148 words)](https://savrn.com/models/mxbai-rerank-xsmall-v1/card) ## Configuration Architecture DebertaV2ForSequenceClassification Context length (tokens) 512 Layers 12 Hidden size 384 Feed-forward size 1,536 Attention heads 6 Vocabulary size 128,100 Stored precision float16 Model type deberta-v2 ## Identity and Version Repository mixedbread-ai/mxbai-rerank-xsmall-v1 Publisher Mixedbread Task Text ranking Modality Other Library transformers Parameters 71M parameters Languages en Revision b5c6e9da73abc3711f593f705371cdbe9e0fe422 First published 2024-02-29 Last updated 2025-04-02 ## Files and Weights 13 files, 524.3 MB in total. The weights are 3 files totalling 513.1 MB in onnx, safetensors. Weights3 files · 513.1 MB Configuration4 files · 3.2 KB Tokenizer2 files · 8.7 MB Documentation2 files · 60.3 KB Other1 file · 2.5 MB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 141.7 MB | a29bc212faf5 | | onnx/model.onnx | Weights | 284.2 MB | 536b7183f896 | | onnx/model_quantized.onnx | Weights | 87.2 MB | 15ef19a6de90 | | added_tokens.json | Configuration | 23 B | — | | config.json | Configuration | 968 B | — | | onnx/quantize_config.json | Configuration | 1.2 KB | — | | special_tokens_map.json | Configuration | 970 B | — | | LICENSE | Documentation | 10.8 KB | — | | README.md | Documentation | 49.5 KB | — | | spm.model | Other | 2.5 MB | c679fbf93643 | | .gitattributes | Repository | 1.5 KB | — | | tokenizer.json | Tokenizer | 8.6 MB | — | | tokenizer_config.json | Tokenizer | 1.4 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 513.1 MB [Download from Mixedbread](https://huggingface.co/mixedbread-ai/mxbai-rerank-xsmall-v1) Released by Mixedbread through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 513.1 MB | | 16-bit | 0.1 GB | | 8-bit | 0.1 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About mxbai-rerank-xsmall-v1 ### How much GPU memory does mxbai-rerank-xsmall-v1 need? About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (71M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run mxbai-rerank-xsmall-v1 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 mxbai-rerank-xsmall-v1 commercially? Yes. mxbai-rerank-xsmall-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. ### What is mxbai-rerank-xsmall-v1's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text ranking ### [ms-marco-MiniLM-L12-v2](https://savrn.com/models/ms-marco-minilm-l12-v2) [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 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/ms-marco-minilm-l12-v2) 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) Model · Text ranking ### [qnli-electra-base](https://savrn.com/models/qnli-electra-base) [Sentence Transformers - Cross-Encoders](https://savrn.com/model-publishers/cross-encoder) This model was trained using SentenceTransformers Cross-Encoder class. Given a question and paragraph, can the question be answered by the paragraph? The models have been trained on the GLUE QNLI dataset, which transformed the SQuAD dataset into an NLI task. For performance results of this model, see [SBERT.net Pre-trained Cross-Encoder][https://www.sbert.net/docs/pretrainedcross-encoders.html]. Pre-trained models can be used like this: You can use the model also directly with Transformers library (without SentenceTransformers library) Open weights apache-2.0 109M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/qnli-electra-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-MiniLM-L6-v2](https://savrn.com/models/ms-marco-minilm-l6-v2) [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 with 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 23M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/ms-marco-minilm-l6-v2) Model · Text ranking ### [ms-marco-MiniLM-L4-v2](https://savrn.com/models/ms-marco-minilm-l4-v2) [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 19M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/ms-marco-minilm-l4-v2) ## Mixedbread [All models and datasets](https://savrn.com/model-publishers/mixedbread-ai) ## Versions - [b5c6e9da73ab](https://savrn.com/models/mxbai-rerank-xsmall-v1/versions/b5c6e9da73ab) · current 2026-09-18 ## Explore More - [All text ranking models](https://savrn.com/models/tasks/text-ranking) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [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. - [Hugging Face record](https://huggingface.co/mixedbread-ai/mxbai-rerank-xsmall-v1) - [How the hub is built](https://savrn.com/model-hub/methodology)