Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality

IBM released Granite Embedding Multilingual R2, an open-source multilingual embedding model under Apache 2.0 license. It supports a 32K token context window and offers top retrieval quality for models under 100 million parameters. This advancement improves multilingual text retrieval and understanding in smaller, efficient models.

ArchiveLaunchHigh-signal source

Signal trust

High-signal sourceSingle sourceEarly signal

Market reactionIBM ↓ -0.54% by next close

PublishedThursday, May 14, 2026 at 8:55 PMMay 14, 08:55 PM

FreshnessArchive

Story ID#969

Back to feed Original report

Original article excerpt

Server-side extracted preview paragraphs from the original source.

A Blog post by IBM Granite on Hugging Face

In this post: Enterprise-Ready by Design · A Strong Sub-100M Multilingual Model · What Changed from R1 · Training the Full-Size 311M Model · Building the compact 97M Multilingual Model · Benchmark Results · Matryoshka Embeddings · Deployment Options · For Framework Integrators · Which Model Should You Use? · Try The Models

Multilingual embedding models face a persistent tension: broad language coverage usually comes at the cost of model size, and small models usually sacrifice languages. If you work across languages — retrieval-augmented generation over multilingual corpora, cross-lingual search, code retrieval in international teams — you've likely had to choose between a model that's fast enough and one that's good enough.

Opening the briefing

Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality

Original article excerpt