The publication AI reads — a remote MCP server, nothing to install.Connect your agent →
Model register·ibm-granite

ibm-granite/granite-embedding-125m-english

ibm-granite/granite-embedding-125m-english is a ibm-granite record on this register. The Hugging Face model API lists the pipeline tag as sentence-similarity. The safetensors index gives an exact parameter count of 124,645,632. Architectural context length (max_position_embeddings) is 514. The listed licence is apache-2.0. The Hub repository was created on 4 Dec 2024, which is the release date this register uses.

Primary source: the Hugging Face model card for ibm-granite/granite-embedding-125m-english. Fields below come from that card, the Hub model API, and the repository’s own config.json when those files exist. A field we cannot source is omitted rather than guessed.

Organisationibm-granite
ReleasedRepo creation date on Hugging Face4 Dec 2024
Last modified19 Aug 2025
ParametersExact, from the safetensors index125M 124,645,632
Context lengthmax_position_embeddings — architectural maximum, not necessarily served514 514
Licenceapache-2.0
Pipeline / taskpipeline_tag on the Hugging Face model APIsentence-similarity
File formatsONNX, safetensors
Librarylibrary_name on the Hugging Face model APIsentence-transformers
Architectureroberta
Layers12
Vocabulary50,265
DownloadsAt last check203.9k
Likes38
GatedNo

How to run

Safetensors weights are on the Hugging Face repository. The parameter count on this page came from that index.

The Hugging Face model API lists the library as sentence-transformers.

Load it from huggingface.co/ibm-granite/granite-embedding-125m-english. This page does not add install steps that the Hub files do not state.

Agent capabilities

This model publishes no chat template, so there is nothing to inspect. That is not evidence of missing support — many base models and some releases simply ship without one.

Questions this record can answer

When was granite-embedding-125m-english released?
The Hugging Face repository was created on 4 Dec 2024, which is the date this register uses.
How many parameters does granite-embedding-125m-english have?
The safetensors index gives 124,645,632 parameters, shown here as 125M. That figure is exact, not rounded.
What is the context length of granite-embedding-125m-english?
514 tokens. That is max_position_embeddings from the model's own config.json — the architectural maximum, not necessarily the context a provider serves.
What licence is granite-embedding-125m-english under?
The Hub card lists apache-2.0.
Is granite-embedding-125m-english gated?
No. The Hugging Face model API does not mark this repository as gated.

Where each field came from

  • Hugging Face model API — releasedAt, lastModified, downloads, likes, task, license, gated, parameters, libraryName, formats. Checked 3 Nov 2026.
  • config.json — contextLength, layers, vocabSize, architecture. Checked 3 Nov 2026.

First recorded 1 Nov 2026, last checked 3 Nov 2026. This record is compiled automatically from the sources above. Where a field is blank, we could not source it and have not guessed. Canonical repository: huggingface.co/ibm-granite/granite-embedding-125m-english.