Model reference · open weights
granite-embedding-multilingual-r2 is an open-weight embedding model from ibm-granite, 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.
About
Granite-Embedding-97M-Multilingual-R2 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. What's New in R2 - 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 vLL
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | ibm-granite |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 97M |
| Context | 32k tokens |
| Variants | 2 |
| Runs with | sentence-transformers |
| Released | 2026-04-20 |
| Popularity | 95k downloads / month |
| Likes | 137 |
| Licence | Open weights |
How it works
Variants
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.
Using it via the API
Once AxForge deploys granite-embedding-multilingual-r2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (granite-embedding-multilingual-r2 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":"granite-embedding-multilingual-r2","input":"text to embed"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Sources
Explore