Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality
• 14
AI & ML interests
Enterprise-grade AI models
Recent Activity
View all activity
Papers
ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion
Articles
Organization Card
IBM Granite
Granite is a family of open, enterprise-grade AI models that are performant, efficient, and trustworthy.
- 🤖 Granite SLMs - Our latest language models, faster, leaner, and built for agentic workloads.
- 👁️🗨️ Granite Vision - VLM with a special emphasis on document-related tasks.
- 🐥 Granite Docling - Document models for enterprise document workflows.
- 🗣️ Granite Speech - Models for automatic speech recognition and spoken language understanding.
- 📚 Granite Embedding - High-quality embedding models for RAG and semantic search.
- 🦺 Granite Guardian - Safety and content moderation models for responsible AI deployments.
- 📈 Granite Time Series - Models purpose-built for enterprise time series data.
- 🧩 Granite Libraries - Libraries of adapters that supercharge a wide range of capabilities.
Resources
- 📖 Docs: ibm.com/granite/docs/models/granite
- 🧪 Playground: ibm.com/granite/playground
- 🐙 GitHub: github.com/ibm-granite
Models for parsing complex PDFs and structured documents, designed to complement Docling.
-
ibm-granite/granite-docling-258M
Image-Text-to-Text • 0.3B • Updated • 423k • 1.18k -
ibm-granite/granite-docling-258M-mlx
Image-Text-to-Text • 0.3B • Updated • 3.66k • 94 -
granite-docling-258M demo
📝276Extract and convert document content from images
-
Granite Docling 258M WebGPU
🐣158Convert document images to editable HTML
Efficient language models for multilingual generation, coding, RAG, and AI assistant workflows.
Models for parsing complex PDFs and structured documents, designed to complement Docling.
-
ibm-granite/granite-docling-258M
Image-Text-to-Text • 0.3B • Updated • 423k • 1.18k -
ibm-granite/granite-docling-258M-mlx
Image-Text-to-Text • 0.3B • Updated • 3.66k • 94 -
granite-docling-258M demo
📝276Extract and convert document content from images
-
Granite Docling 258M WebGPU
🐣158Convert document images to editable HTML
spaces 11
Runtime error
Agents
41
Multimodal RAG with Granite Vision
🚀
RAG example using Granite [vision, embedding, instruct]
Running on Zero
Agents
Granite Embedding R2 Models Demo
🔍
Rank passages by relevance to a query using embeddings
Running on Zero
Agents
31
Granite 4.0 1B Speech
🎧
Granite 4.0 1B Speech recognition and translation demo
Running
Featured
28
Granite Speech WebGPU
🎙
Transcribe and translate audio to text directly in your browser
Running on Zero
Agents
7
Granite Vision Document Intelligence
🚀
Document intelligence with Granite-Vision-4.1-4B
models 208
ibm-granite/granite-embedding-97m-multilingual-r2
Feature Extraction • 97.4M • Updated • 11.3k • • 99
ibm-granite/granite-4.0-1b-speech-GGUF
2B • Updated • 173
ibm-granite/granite-speech-4.1-2b-GGUF
2B • Updated • 359
ibm-granite/granitelib-rag-r1.0
14.4M • Updated • 39.4k • 27
ibm-granite/granite-switch-4.1-30b-preview
Text Generation • 32B • Updated • 117 • 1
ibm-granite/granite-switch-4.1-8b-preview
Text Generation • 10B • Updated • 172 • 4
ibm-granite/granite-switch-4.1-3b-preview
Text Generation • 4B • Updated • 2.46k • 4
ibm-granite/granitelib-guardian-r1.0
Text Generation • Updated • 11.3k • 21
ibm-granite/granitelib-core-r1.0
Text Generation • Updated • 10.5k • 18
ibm-granite/granite-vision-4.1-4b
Image-Text-to-Text • 4B • Updated • 26.2k • 74