Skip to main content
Watch: I Built an AI App Without Leaving Databricks

IBM - Open weights - verified

Granite Embedding 311M Multilingual R2 embeddings

Granite Embedding 311M Multilingual R2 is a current embedding model from IBM, with open weights on Hugging Face at ibm-granite/granite-embedding-311m-multilingual-r2. It returns 768-dimension vectors by default and accepts up to 32,768 input tokens, for text and code input. There is no API price: the weights download from Hugging Face under Apache 2.0, and you pay for the compute you run them on.

CurrentModel id: ibm-granite/granite-embedding-311m-multilingual-r2- weights: ibm-granite/granite-embedding-311m-multilingual-r2

Default dims
768
Max input
32,768 tok
Price / 1M
Self-hosted
Inputs
Text, Code

Dimensions

Flexible output size
  • 768default
  • 512
  • 384
  • 256
  • 128

Default output: 768 dimensions.

Listed sizes: 768, 512, 384, 256 and 128.

IBM documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

Pricing

No API price: the weights are on Hugging Face and you run them on your own hardware or host.

Open weights

License
Apache 2.0apache-2.0
Commercial use
Commercial use allowedCommercial use is allowed, per the license.
Parameters
312M (311,664,384)

Worth knowing

ModernBERT-based model with CLS pooling covering 200+ languages (enhanced support for 52 plus code), shipped with ONNX and OpenVINO weights, and the card notes Ollama does not support it.

Released . Multilingual: yes.

Usage

Copied verbatim from the page linked below. Placeholders such as project ids and API keys are the source's own.

Python
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("ibm-granite/granite-embedding-311m-multilingual-r2")

# Full 768-dimensional embeddings
full_embeddings = model.encode(["example text"])
print(full_embeddings.shape)  # (1, 768)

# Truncated to 256 dimensions - still effective for many retrieval tasks
truncated_embeddings = model.encode(["example text"], truncate_dim=256)
print(truncated_embeddings.shape)  # (1, 256)

Source: huggingface.co/ibm-granite/granite-embedding-311m-multilingual-r2

FAQ

How many dimensions does Granite Embedding 311M Multilingual R2 output?

Default output: 768 dimensions. Listed sizes: 768, 512, 384, 256 and 128. IBM documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

What is the max input length of Granite Embedding 311M Multilingual R2?

32,768 tokens per input, per the model card. Longer text has to be chunked before you embed it.

Can I use Granite Embedding 311M Multilingual R2 commercially?

Granite Embedding 311M Multilingual R2 is released under Apache 2.0, and commercial use is allowed. The license text is at https://www.apache.org/licenses/LICENSE-2.0.

What can Granite Embedding 311M Multilingual R2 embed?

Text and code input, per the provider. It is documented as multilingual.

Sources

Last verified from the pages below.

Other open-weight embedding models

Default dimensions and max input tokens for the other models you can run yourself.

All embedding models - Open-weight embedding models

Newsletter

New models, every week

One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.

Keep exploring

Model API pricing and specs

First-party prices per 1M tokens for chat and reasoning models.

Local models

Open-weight LLMs you can download and run, with sizes and licenses.

What is RAG?

Where embeddings fit in a retrieval pipeline, end to end.

Vector databases compared

Where the vectors go once you have picked a model.