Granite Docling is a multimodal Image-Text-to-Text model engineered for efficient document conversion. It preserves the core features of Docling while maintaining seamless integration with DoclingDocuments to ensure full compatibility. Granite Docling 258M builds upon the Idefics3 architecture, but introduces two key modifications: it replaces the vision encoder with siglip2-base-patch16-512 and substitutes the language model with a Granite 165M LLM. Try out our Granite-Docling-258 demo today. - **Developed by**: IBM Research - **Model type**: Multi-modal model (image+text-to-text) - **Language(s)**: English (NLP) - **License**: Apache 2.0 - **Release Date**: September 17, 2025

翻訳待ち・原文を表示

画像質問応答

入力テキスト · 画像→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-docling-258M-GGUF

ibm-granite

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

基本情報を収録・詳細は順次追加

分類準備中

入力未確認→ 出力未確認

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-docling-258M-mlx

ibm-granite

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

画像質問応答

入力テキスト · 画像→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-107m-multilingual

ibm-granite

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

埋め込みと類似度

入力テキスト→ 出力埋め込み

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-125m-english

ibm-granite

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

埋め込みと類似度

入力テキスト→ 出力埋め込み

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-278m-multilingual

ibm-granite

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

埋め込みと類似度

入力テキスト→ 出力埋め込み

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-30m-english

ibm-granite

**Model Summary:** Granite-Embedding-30m-English is a 30M parameter dense bi-encoder embedding model from the Granite Embeddings suite that can be used to generate high quality text embeddings. This model produces embedding vectors of size 384 and is trained using a combination of open source relevance-pair datasets with permissive, enterprise-friendly license, and IBM collected and generated datasets. While maintaining competitive scores on academic benchmarks such as BEIR, this model also performs well on many enterprise use cases. This model is developed using retrieval oriented pre-training, contrastive fine-tuning, knowledge distillation and model merging for improved performance. ***Granite-embedding-30m-r1.1*** was specifically designed to support multi-turn information retrieval and is designed to handle contextual document retrieval in multi-turn conversational information retrieval. Granite-embedding-30m-r1.1 was trained on data tailored for multi-turn conversational information retrieval and uses multi-teacher distillation over granite-embedding-30m-english (https://huggingface.co/ibm-granite/granite-embedding-30m-english) - **Developers:** Granite Embedding Team, IBM - **GitHub Repository:** ibm-granite/granite-embedding-models - **Website**: Granite Docs - **Paper:** Technical Report - **Release Date**: August 29, 2025 (granite-embedding-30m-english-r1.1) - **License:** Apache 2.0

翻訳待ち・原文を表示

埋め込みと類似度

入力テキスト→ 出力埋め込み

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-30m-sparse

ibm-granite

**Model Summary:** Granite-Embedding-30m-Sparse is a 30M parameter sparse biencoder embedding model from the Granite Experimental suite that can be used to generate high quality text embeddings. This model produces variable length bag-of-word like dictionary, containing expansions of sentence tokens and their corresponding weights and is trained using a combination of open source relevance-pair datasets with permissive, enterprise-friendly license, and IBM collected and generated datasets. While maintaining competitive scores on academic benchmarks such as BEIR, this model also performs well on many enterprise use cases. This model is developed using retrieval oriented pretraining, contrastive finetuning and knowledge distillation for improved performance. **Intended use:** The model is designed to produce variable length bag-of-word like dictionary, containing expansions of sentence tokens and their corresponding weights, for a given text, which can be used for text similarity, retrieval, and search applications. The model can then be used to encode pairs of text and find the similarity between their representations

翻訳待ち・原文を表示

埋め込みと類似度

入力テキスト→ 出力埋め込み

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-311m-multilingual-r2

ibm-granite

**Model Summary:** Granite-Embedding-311M-Multilingual-R2 is a 311M parameter dense embedding model from the Granite Embeddings collection for high-quality multilingual text embeddings. It produces 768-dimensional vectors with a context length of up to 32,768 tokens. The model supports **200+ languages** (based on the multilingual pretraining corpus of the underlying encoder), with enhanced support for 52 languages and programming code that receive explicit retrieval-pair and cross-lingual training. All training data uses permissive, enterprise-friendly licenses, plus IBM-collected and IBM-generated datasets. > Granite Embedding 311M Multilingual R2 shows strong performance across multilingual information retrieval benchmarks, code retrieval, long-document search, conversational multi-turn, and reasoning retrieval tasks. The multilingual R2 model scores **65.2** on Multilingual MTEB Retrieval (18 tasks) — a **+13 point improvement** over granite-embedding-278m-multilingual (52.2) — and averages **56.3** across all retrieval benchmarks, representing a **+14.5 point gain** over the previous generation. It supports Matryoshka dimension reduction, 32k-token context, and ships with ONNX and OpenVINO models for production deployment. - **Architecture upgrade:** ModernBERT replaces XLM-RoBERTa, bringing alternating attention, GeGLU activations, and rotary position embeddings. - **Extended context:** 32,768 tokens (up from 512 in R1), enabling long-document and multi-passage retrieval. - **Expanded vocabulary:** 262K multilingual tokenizer trained on text and code across 200+ languages. - **Matryoshka support:** Truncate embeddings to 512, 384, 256, or 128 dimensions with graceful degradation. - **Broader code coverage:** Code retrieval supported for Python, Go, Java, JavaScript, PHP, Ruby, SQL, C, C++. - **Training advances:** Knowledge distillation from multiple teachers, contrastive fine-tuning, and model merging yield +14.5 points on average retrieval benchmarks. - **Deployment flexibility:** Released with ONNX and OpenVINO models; compatible with vLLM and llama.cpp (GGUF).

翻訳待ち・原文を表示

埋め込みと類似度

入力テキスト→ 出力埋め込み

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-97m-multilingual-r2

ibm-granite

**Model Summary:** Granite-Embedding-97M-Multilingual-R2 is a 97M parameter dense embedding model from the Granite Embeddings collection for high-quality multilingual text embeddings at minimal compute cost. It produces 384-dimensional vectors with a context length of up to 32,768 tokens. The model supports **200+ languages** (based on the multilingual pretraining corpus of the underlying encoder), with **enhanced support for 52 languages and programming code** that receive explicit retrieval-pair and cross-lingual training. All training data uses permissive, enterprise-friendly licenses, plus IBM-collected and IBM-generated datasets. > Granite Embedding 97M Multilingual R2 scores **60.3** on Multilingual MTEB Retrieval (18 tasks) — the highest retrieval score of any open multilingual embedding model under 100M parameters, outperforming the next-best model in its size class (multilingual-e5-small at 50.9) by **+9.4 points** — while being roughly **3× smaller** than the full-size granite-embedding-311m-multilingual-r2. The multilingual R2 model shows strong performance across multilingual information retrieval benchmarks, code retrieval, long-document search, conversational multi-turn, and reasoning retrieval tasks. - **Architecture upgrade:** ModernBERT replaces XLM-RoBERTa, bringing alternating attention, SiLU activations, and rotary position embeddings. - **Extended context:** 32,768 tokens (up from 512 in R1), enabling long-document and multi-passage retrieval. - **Compact multilingual vocabulary:** A purpose-trained 180K-token tokenizer preserves broad multilingual coverage while reducing model size. - **Model pruning:** Layer pruning (22 → 12 layers) from the full-size multilingual model, followed by continued distillation training to recover quality. - **Broader code coverage:** Code retrieval training set that includes Python, Go, Java, JavaScript, PHP, Ruby, SQL, C, C++. - **Training advances:** Knowledge distillation from multiple teachers and contrastive fine-tuning yield a **+14.6 point** average gain over the previous-generation granite-embedding-107m-multilingual. - **Deployment flexibility:** Released with ONNX and OpenVINO models; compatible with vLLM and llama.cpp (GGUF).

翻訳待ち・原文を表示

埋め込みと類似度

入力テキスト→ 出力埋め込み

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-english-r2

ibm-granite

**Model Summary:** Granite-embedding-english-r2 is a 149M 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 768 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-english-r2 is optimized to ensure strong alignment between query and passage embeddings.

翻訳待ち・原文を表示

埋め込みと類似度

入力テキスト→ 出力埋め込み

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-reranker-english-r2

ibm-granite

**Model Summary:** _granite-embedding-reranker-english-r2_ is a 149M parameter dense cross-encoder model from the Granite Embeddings collection that can be used to generate high quality text embeddings. This model produces embedding vectors of size 768 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 _granite-embedding-reranker-english-r2_ model uses a cross-encoder architecture to compute high-quality relevance scores between queries and documents by jointly encoding their text, enabling precise reranking based on contextual alignment. The model is trained with ranking-specific loss functions such as pListMLE, along with model merging techniques to enhance performance. The reranker model shows strong performance on standard information retrieval benchmark (BEIR, MIRACL), long-document search benchmarks (MLDR), and on many enterprise use cases. The latest granite embedding r2 release introduces two English embedding models, and one English reranking all based on the ModernBERT architecture: - _granite-embedding-english-r2_ (**149M** parameters): with an output embedding size of _768_, replacing _granite-embedding-125m-english_. - _granite-embedding-small-english-r2_ (**47M** parameters): A _first-of-its-kind_ reduced-size model, with 8192 context length support, fewer layers and a smaller output embedding size (_384_), replacing _granite-embedding-30m-english_. - **_granite-embedding-reranker-english-r2_** (**149M** parameters): reranker model based on _granite-embedding-english-r2_, with an output embedding size of _768_.

翻訳待ち・原文を表示

分類準備中

入力未確認→ 出力未確認

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗

granite-embedding-small-english-r2

ibm-granite

**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.

翻訳待ち・原文を表示

テキスト分析オープンウェイト

入力テキスト→ 出力テキスト

料金未確認マルチモーダル・チャネル料金は個別に確認

詳細を見る ↗

比較に追加出典・文書 ↗