Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality
May 4, 2026
Summary
Introduces the ibm-granite/granite-4.1-8b model, an open Apache 2.0 multilingual embedding model with a 32K context window, designed for high retrieval quality and efficient operation within sub-100M parameter constraints.
More from the Sentence Transformers for Playlist Generation trail
- NeoMME: an efficient Multimodal-native and Multilingual Encoder
- MTEB: Massive Text Embedding Benchmark
- Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis
- Build a Domain-Specific Embedding Model in Under a Day
- Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers