# gte-small by Dingkun Long: Open-Weight Model Source: https://savrn.com/models/gte-small Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve gte-small (33M 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 | 0.1 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 | | 8-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 | | 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 23, 2026. [gte-small on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/gte-small/gpus) ## SAVRN's Notes on gte-small One tenth of a gigabyte. That is the 16-bit weight figure for gte-small, and the memory need matches it at 0.1 GB, so the cheapest slot we price, one MI300X with 192 GB at $1.85 per hour on-demand, has close to two thousand times the room this model wants. Put it beside the generator that already occupies the card and embed on the margin. The 512-token context sets the longest passage per pass. MIT terms allow commercial use, modification and redistribution as long as the copyright and permission notices ship with the files, so an on-site embedding service has nothing to negotiate. Check that 512 tokens fits your chunking plan, and know that the same line offers GTE-base and GTE-large if you need more model; the paper is arXiv:2308.03281. Access is open, the last update landed 2024-11-16, and the Index carries no host price for it yet. SAVRN Research, 2026-09-18 ## Model Card By Dingkun Long, published under mit, revision 17e1f347d17f. General Text Embeddings (GTE) model. [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://savrn.com/papers/towards-general-text-embeddings-with-multi-stage-contrastive-learning) The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including [GTE-large](https://savrn.com/models/gte-large), [GTE-base](https://huggingface.co/thenlper/gte-base), and [GTE-small](https://savrn.com/models/gte-small). The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc. ### Metrics We compared the performance of the GTE models with other popular text embedding models on the MTEB benchmark. For more detailed comparison results, please refer to the [MTEB leaderboard](https://huggingface.co/spaces/mteb/leaderboard). [Read the full model card (512 words)](https://savrn.com/models/gte-small/card) ## Configuration Architecture BertModel Context length (tokens) 512 Layers 12 Hidden size 384 Feed-forward size 1,536 Attention heads 12 Vocabulary size 30,522 Stored precision float16 Model type bert ## Identity and Version Repository thenlper/gte-small Publisher Dingkun Long Task Sentence similarity Modality Text Library sentence-transformers Parameters 33M parameters Languages en Revision 17e1f347d17fe144873b1201da91788898c639cd First published 2023-07-27 Last updated 2024-11-16 ## Files and Weights 23 files, 802.9 MB in total. The weights are 10 files totalling 800.9 MB in bin, h5, mlmodel, onnx, safetensors. Weights10 files · 800.9 MB Configuration6 files · 2.0 KB Tokenizer3 files · 943.6 KB Documentation1 file · 68.1 KB Other2 files · 1.0 MB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | coreml/feature-extraction/float32_model.mlpackage/Data/com.apple.CoreML/model.mlmodel | Weights | 122.0 KB | 33e5309eae5a | | coreml/feature-extraction/float32_model.mlpackage/Data/com.apple.CoreML/weights/weight.bin | Weights | 133.1 MB | d6d0949a2bd6 | | model.safetensors | Weights | 66.7 MB | 9a1eb90bbac3 | | onnx/model.onnx | Weights | 133.1 MB | 0b01312b59be | | onnx/model_O4.onnx | Weights | 66.6 MB | f39634c5a62a | | onnx/model_qint8_avx512_vnni.onnx | Weights | 34.1 MB | c9434b8d7161 | | openvino/openvino_model.bin | Weights | 132.9 MB | 6202050706e8 | | openvino/openvino_model_qint8_quantized.bin | Weights | 33.8 MB | fa05bae0e1b0 | | pytorch_model.bin | Weights | 66.8 MB | 344099675ece | | tf_model.h5 | Weights | 133.7 MB | 38d78f5cca85 | | 1_Pooling/config.json | Configuration | 190 B | — | | config.json | Configuration | 583 B | — | | coreml/feature-extraction/float32_model.mlpackage/Manifest.json | Configuration | 617 B | — | | modules.json | Configuration | 385 B | — | | sentence_bert_config.json | Configuration | 57 B | — | | special_tokens_map.json | Configuration | 125 B | — | | README.md | Documentation | 68.1 KB | — | | openvino/openvino_model.xml | Other | 363.1 KB | — | | openvino/openvino_model_qint8_quantized.xml | Other | 664.1 KB | — | | .gitattributes | Repository | 1.5 KB | — | | tokenizer.json | Tokenizer | 711.7 KB | — | | tokenizer_config.json | Tokenizer | 394 B | — | | vocab.txt | Tokenizer | 231.5 KB | — | ## License and Download License mit Access Open weights, no gate Download size 800.9 MB [Download from Dingkun Long](https://huggingface.co/thenlper/gte-small) Released by Dingkun Long through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Described by [arXiv:2308.03281](https://savrn.com/papers/towards-general-text-embeddings-with-multi-stage-contrastive-learning) ## Evaluations Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical. | Benchmark | Conditions | Result | Reported by | Revision | Date | | --- | --- | --- | --- | --- | --- | | MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 73.2239 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric apComparison conditions not established | 36.099 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 67.3206 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric accuracyComparison conditions not established | 91.8189 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric apComparison conditions not established | 88.524 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric f1Comparison conditions not established | 91.8037 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 48.032 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 47.4491 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1Comparison conditions not established | 30.725 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_10Comparison conditions not established | 46.604 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_100Comparison conditions not established | 47.535 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1000Comparison conditions not established | 47.538 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_3Comparison conditions not established | 41.833 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_5Comparison conditions not established | 44.61 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1Comparison conditions not established | 31.223 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_10Comparison conditions not established | 46.794 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_100Comparison conditions not established | 47.725 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1000Comparison conditions not established | 47.727 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_3Comparison conditions not established | 42.07 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_5Comparison conditions not established | 44.812 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1Comparison conditions not established | 30.725 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_10Comparison conditions not established | 55.441 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_100Comparison conditions not established | 59.134 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1000Comparison conditions not established | 59.199 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_3Comparison conditions not established | 45.599 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_5Comparison conditions not established | 50.637 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1Comparison conditions not established | 30.725 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_10Comparison conditions not established | 8.364 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_100Comparison conditions not established | 0.991 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1000Comparison conditions not established | 0.1 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_3Comparison conditions not established | 18.848 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_5Comparison conditions not established | 13.77 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1Comparison conditions not established | 30.725 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_10Comparison conditions not established | 83.642 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_100Comparison conditions not established | 99.147 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1000Comparison conditions not established | 99.644 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_3Comparison conditions not established | 56.543 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_5Comparison conditions not established | 68.848 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArxivClusteringP2P | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 47.9018 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | | MTEB ArxivClusteringS2S | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 40.2573 | [thenlper](https://huggingface.co/thenlper/gte-small) Publisher reported | Evaluated revision not stated | — | ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 800.9 MB | | 16-bit | 0.1 GB | | 8-bit | 0.0 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Compare gte-small - [all-MiniLM-L12-v2 vs gte-small](https://savrn.com/models/compare/all-minilm-l12-v2-vs-gte-small) ## Questions About gte-small ### How much GPU memory does gte-small need? About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (33M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run gte-small 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 gte-small commercially? Yes. gte-small is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included. ### What is gte-small's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Sentence similarity ### [all-MiniLM-L12-v2](https://savrn.com/models/all-minilm-l12-v2) [Sentence Transformers](https://savrn.com/model-publishers/sentence-transformers) This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. 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 have to apply the right pooling-operation on-top of the contextualized word embeddings. The project aims to train sentence embedding models on very large sentence level datasets using a self-supervised contrastive learning objective. We used the pretrained… Open weights apache-2.0 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/all-minilm-l12-v2) Model · Sentence similarity ### [e5-small-v2](https://savrn.com/models/e5-small-v2) [Liang Wang](https://savrn.com/model-publishers/intfloat) Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022 This model has 12 layers and the embedding size is 384. Below is an example to encode queries and passages from the MS-MARCO passage ranking dataset. Please refer to our paper at https://arxiv.org/pdf/2212.03533.pdf. Check out unilm/e5 to reproduce evaluation results on the BEIR and MTEB benchmark. Below is an example for usage with sentencetransformers. Package requirements pip install sentencetransformers~=2.2.2 1. Do I need to add the prefix "query: " and "passage: " to input texts? Yes, this is how the model is trained, otherwise you will see a performance degradation.… Open weights mit 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/e5-small-v2) Model · Sentence similarity ### [AtmicQuoterv3](https://savrn.com/models/atmicquoterv3) [Atmic Intelligence Project- Sri Ramanasramam](https://savrn.com/model-publishers/sriramanaatmic) Fine-tuned from BAAI/bge-small-en-v1.5 (MultipleNegativesRankingLoss, 3 epochs, batch size 16, lr 2e-5) on the combined AtmicQuoterv1 + AtmicQuoterv3 training data, for exact-citation retrieval over Sri Ramana Maharshi's teachings. Queries are encoded with the BGE query instruction (Represent this sentence for searching relevant passages: ); passages are not. Validation set: 1,006 queries (48 from the root validation.jsonl + 958 from AtmicQuoterv1's validation split). Corpus: 8,742 unique passages (AtmicQuoterv1's corpus and the full citation/RAGcitation.json corpus, after the text normalization described below). "alone" = dense retrieval only, ranking the full corpus. "hybrid BM25" =… Open weights 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/atmicquoterv3) Model · Sentence similarity ### [bge-small-vscode-dup](https://savrn.com/models/bge-small-vscode-dup) [Musab Suhail](https://savrn.com/model-publishers/musab6969) This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more. First install the Sentence Transformers library: Then you can load this model and run inference. Evaluated with EmbeddingSimilarityEvaluator Approximate statistics based on the first 100 samples: "scale": 20.0, "similarityfct": "cossim", "gatheracrossdevices": false, "directions": [ "querytodoc" "partitionmode": "joint", "hardnessmode": null, "hardnessstrength": 0.0 bibtex title = "Sentence-BERT: Sentence Embeddings using… Open weights 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/bge-small-vscode-dup) Model · Sentence similarity ### [snowflake-arctic-embed-s](https://savrn.com/models/snowflake-arctic-embed-s) [Snowflake](https://savrn.com/model-publishers/snowflake) 12/04/2024: Release of snowflake-arctic-embed-l-v2.0 and snowflake-arctic-embed-m-v2.0 our newest models with multilingual workloads in mind. These models outperform prior versions of Arctic Embed and we suggest these replace prior versions! 07/26/2024: Release preprint [[2407.18887] Embedding And Clustering Your Data Can Improve Contrastive Pretraining](https://arxiv.org/abs/2407.18887) on arXiv. 07/18/2024: Release of snowflake-arctic-embed-m-v1.5, capable of producing highly compressible embedding vectors that preserve quality even when squished as small as 128 bytes per vector. Details about the development of this model are available in the launch post on the Snowflake engineering… Open weights apache-2.0 33M parameters 512 tokens sentence-transformers [View model](https://savrn.com/models/snowflake-arctic-embed-s) Model · Sentence similarity ### [rubert-tiny2](https://savrn.com/models/rubert-tiny2) [David Dale](https://savrn.com/model-publishers/cointegrated) This is an updated version of cointegrated/rubert-tiny: a small Russian BERT-based encoder with high-quality sentence embeddings. This post in Russian gives more details. The differences from the previous version include: - sentence embeddings approximate LaBSE closer than before; - meaningful segment embeddings (tuned on the NLI task) - the model is focused only on Russian. The model should be used as is to produce sentence embeddings (e.g. for KNN classification of short texts) or fine-tuned for a downstream task. Sentence embeddings can be produced as follows: Alternatively, you can use the model with sentencetransformers: For those who want to run the inference with VLLM, there is a… Open weights mit 29M parameters 2,048 tokens sentence-transformers [View model](https://savrn.com/models/rubert-tiny2) ## Dingkun Long [All models and datasets](https://savrn.com/model-publishers/thenlper) ## Versions - [17e1f347d17f](https://savrn.com/models/gte-small/versions/17e1f347d17f) · current 2026-10-23 ## Explore More - [All sentence similarity models](https://savrn.com/models/tasks/sentence-similarity) - [All models under mit](https://savrn.com/models/licenses/mit) - [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/thenlper/gte-small) - [How the hub is built](https://savrn.com/model-hub/methodology)