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

ibm-granite/granite-4.1-30b

ibm-granite/granite-4.1-30b is a ibm-granite record on this register. The Hugging Face model API lists the pipeline tag as text-generation. The safetensors index gives an exact parameter count of 28,865,728,512. Architectural context length (max_position_embeddings) is 131,072. The listed licence is apache-2.0. The Hub repository was created on 6 Apr 2026, which is the release date this register uses.

Primary source: the Hugging Face model card for ibm-granite/granite-4.1-30b. 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 Face6 Apr 2026
Last modified4 May 2026
ParametersExact, from the safetensors index28.9B 28,865,728,512
Context lengthmax_position_embeddings — architectural maximum, not necessarily served128K 131,072
Licenceapache-2.0
Pipeline / taskpipeline_tag on the Hugging Face model APItext-generation
File formatssafetensors
Architecturegranite
Layers64
Vocabulary100,352
DownloadsAt last check186.9k
Likes148
GatedNo

How to run

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

Load it from huggingface.co/ibm-granite/granite-4.1-30b. This page does not add install steps that the Hub files do not state.

Agent capabilities

Derived from the model’s own chat template, with the match counts behind each finding.

  • ●Tool calling30 matches in template
  • ○Reasoning / thinkingno evidence in template
  • ●System prompt2 matches in template
  • ○Image inputno evidence in template
  • ○Video inputno evidence in template
  • ○Audio inputno evidence in template

Questions this record can answer

When was granite-4.1-30b released?
The Hugging Face repository was created on 6 Apr 2026, which is the date this register uses.
How many parameters does granite-4.1-30b have?
The safetensors index gives 28,865,728,512 parameters, shown here as 28.9B. That figure is exact, not rounded.
What is the context length of granite-4.1-30b?
131,072 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-4.1-30b under?
The Hub card lists apache-2.0.
Is granite-4.1-30b gated?
No. The Hugging Face model API does not mark this repository as gated.
Does the granite-4.1-30b chat template show tool calling?
The chat template contains evidence of tool calling.

Where each field came from

  • Hugging Face model API — releasedAt, lastModified, downloads, likes, task, license, gated, parameters. Checked 15 Oct 2026.
  • config.json — contextLength, layers, vocabSize, architecture. Checked 15 Oct 2026.
  • chat template — capabilities. Checked 15 Oct 2026.

First recorded 24 Sept 2026, last checked 15 Oct 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-4.1-30b.