Open-weight model · Feature extraction

granite-embedding-small-english-r2

by IBM Granite ibm-granite/granite-embedding-small-english-r2

granite-embedding-small-english-r2 is an open-weight model for feature extraction from IBM Granite, released under Apache License 2.0. It has 48M parameters and a 8,192-token context. At 16-bit it needs about 0.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 5.2M downloads a month.

Granite-embedding-small-english-r2 is a 47M parameter dense biencoder embedding model from the Granite Embeddings collection that can be used to generate high quality text embeddings.

Parameters48M

Context8,192

Weights190.7 MB

Licenseapache-2.0

AccessOpen weights

Monthly Downloads5.2M

Runs On

What it takes to serve granite-embedding-small-english-r2 (48M 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 (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	0.0 GB	0.1 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	0.0 GB	0.0 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x 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, read Oct 13, 2026.

granite-embedding-small-english-r2 on every accelerator the SAVRN Index prices, at every precision

SAVRN's Notes on granite-embedding-small-english-r2

8,192 tokens of context on a 48M parameter embedding model change what you can index: a whole document section goes in as one unit. IBM Granite built this r2 release as a dense biencoder on ModernBERT, returning a 384-dimension vector per passage. Memory at 16-bit is 0.1 GB, and the cheapest listed host is one 192 GB MI300X at $1.85 an hour on demand, so plan on sharing that accelerator and paying for the slice of the hour you use.

Apache 2.0 carries an express patent grant, useful when embeddings ship inside a product; keep the license, notices and NOTICE file in the deployment and state significant changes. Before committing, read the training data, open relevance-pair datasets plus IBM's own collected and generated sets, against your data policy, and match the revision, released July 17, 2025 and last updated January 21, 2026, to the one you evaluated.

SAVRN Research, 2026-09-18

Model Card

By IBM Granite, published under apache-2.0, revision 2ab6fa8ea2d6.

Model Summary: Granite-embedding-small-english-r2 is a 47M parameter dense biencoder embedding model from the Granite Embeddings collection that can be used to generate high quality text embeddings. This model produces embedding vectors of size 384 based on context length of upto 8192 tokens. Compared to most other open-source models, this model was only trained using open-source relevance-pair datasets with permissive, enterprise-friendly license, plus IBM collected and generated datasets.

The r2 models show strong performance across standard and IBM-built information retrieval benchmarks (BEIR, ClapNQ), code retrieval (COIR), long-document search benchmarks (MLDR, LongEmbed), conversational multi-turn (MTRAG), table retrieval (NQTables, OTT-QA, AIT-QA, MultiHierTT, OpenWikiTables), and on many enterprise use cases.

These models use a bi-encoder architecture to generate high-quality embeddings from text inputs such as queries, passages, and documents, enabling seamless comparison through cosine similarity. Built using retrieval oriented pretraining, contrastive finetuning, knowledge distillation, and model merging, granite-embedding-small-english-r2 is optimized to ensure strong alignment between query and passage embeddings.

Read the full model card (1,320 words)

Configuration

Architecture: ModernBertModel
Context length (tokens): 8,192
Layers: 12
Hidden size: 384
Feed-forward size: 1,536
Attention heads: 12
Vocabulary size: 50,368
Stored precision: bfloat16
Model type: modernbert

Identity and Version

Repository: ibm-granite/granite-embedding-small-english-r2
Publisher: IBM Granite
Task: Feature extraction
Modality: Text
Library: sentence-transformers
Parameters: 48M parameters
Languages: en
Revision: 2ab6fa8ea2d674564defd37171ae19079b864b33
First published: 2025-07-17
Last updated: 2026-01-21

Files and Weights

11 files, 194.3 MB in total. The weights are 2 files totalling 190.7 MB in bin, safetensors.

Weights2 files · 190.7 MB

Configuration5 files · 2.5 KB

Tokenizer2 files · 3.6 MB

Documentation1 file · 12.4 KB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	95.3 MB	dcbfaf2ee50d
pytorch_model.bin	Weights	95.3 MB	189cd50b38b2
1_Pooling/config.json	Configuration	191 B	—
config.json	Configuration	1.3 KB	—
modules.json	Configuration	230 B	—
sentence_bert_config.json	Configuration	55 B	—
special_tokens_map.json	Configuration	694 B	—
README.md	Documentation	12.4 KB	—
.gitattributes	Repository	1.5 KB	—
tokenizer.json	Tokenizer	3.6 MB	—
tokenizer_config.json	Tokenizer	20.8 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 190.7 MB

Download from IBM Granite

Released by IBM Granite through its official repository on Hugging Face. Read the license.

Built From

Described by arXiv:2508.21085

Memory Requirements

Precision	Weights in memory
As published	190.7 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 granite-embedding-small-english-r2

Questions About granite-embedding-small-english-r2

How much GPU memory does granite-embedding-small-english-r2 need?

About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (48M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run granite-embedding-small-english-r2 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 granite-embedding-small-english-r2 commercially?

Yes. granite-embedding-small-english-r2 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 granite-embedding-small-english-r2's context length?

8,192 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Feature extraction

SheetSage2

Multimodal Art Projection

SheetSage2 turns music recordings into lead sheets and timed musical annotations. Transcribe a complete song, edit its ABC or MIDI, render a piano preview, or extract embeddings and token predictions for your own tools. Built on MERT-v2-FullSong, with adapters that merge automatically when you load the model. 2026-09-21: Fixed missing enharmonic spelling correction for key and chord labels. Chord spelling now follows the local key. This updates key/chord labels and ABC notation without changing musical pitches or timing. If you downloaded the repository or model before this update (2026-09-21), please update to the latest repository code. Model weights are unchanged. Use Python 3.10 or 3.11…

Open weights cc-by-nc-4.0 57M parameters transformers

View model

Model · Feature extraction

bge-small-en-v1.5

Beijing Academy of Artificial Intelligence

More details please refer to our Github: FlagEmbedding. If you are looking for a model that supports more languages, longer texts, and other retrieval methods, you can try using bge-m3. FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently: - 1/30/2024: Release BGE-M3, a new member to BGE model series! M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec/colbert retrieval). It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. Technical…

Open weights mit 33M parameters 512 tokens sentence-transformers

View model

Model · Feature extraction

jina-embeddings-v2-small-en

Jina AI

The easiest way to starting using jina-embeddings-v2-small-en is to use Jina AI's Embedding API. jina-embeddings-v2-small-en is an English, monolingual embedding model supporting 8192 sequence length. It is based on a BERT architecture (JinaBERT) that supports the symmetric bidirectional variant of ALiBi to allow longer sequence length. The backbone jina-bert-v2-small-en is pretrained on the C4 dataset. The model is further trained on Jina AI's collection of more than 400 millions of sentence pairs and hard negatives. These pairs were obtained from various domains and were carefully selected through a thorough cleaning process. The embedding model was trained using 512 sequence length, but…

Open weights apache-2.0 33M parameters 8,192 tokens sentence-transformers

View model

Model · Feature extraction

starwell

Charles Norton

Starwell is a generative model for stellarator design. Given a number of field periods, an aspect ratio and a target magnetic-gradient scale length LgradB, it samples a plasma boundary for the mhdstable problem of the ConStellaration benchmark, predicts its benchmark metrics, and lays out modular coils for it. Boundaries are SurfaceRZFourier dicts (rcos, zsin) that constellaration evaluates directly; sample also takes tau, guidance, steps and seed, and model.config.sampling holds the integrator's defaults. Coils are simsopt CurveXYZFourier coefficients for one half period with their currents, and simsopt.field.coilsviasymmetries builds the full set; limits (in metres and per metre) sets the…

Open weights mit 26M parameters transformers

View model

Model · Feature extraction

Corpus-ViT

Gugu8

A vision encoder with a runtime-selectable token budget, built to sit between an image and an LLM. A coarse 32px grid covers the whole image; a router spends extra 16px detail only on the regions that need it. Output length is 49 + 3k tokens — 49 at k=0, 121 at k=24 — so you choose the tokens/fidelity trade-off per image, at inference, with no retraining. 24.94M parameters. Trained in 6000 steps (~30 min) on 2× Kaggle T4 by distillation from google/siglip-base-patch16-224 (86M). This is a working, honest baseline, not a competitive encoder. On the Flickr30k official test split it reaches 8.95 mean R@1 against the teacher's 83.25 — roughly 10% of its teacher. Chance on 1000 images is 0.10.…

Open weights apache-2.0 25M parameters transformers

View model

Model · Feature extraction

jano-tts

Jano

This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Open weights 25M parameters transformers

View model