Skip to content

Model Library

IBMReleased October 28, 2025

Granite 4.0 1B

IBM · Released October 28, 2025

Intelligence score

2

At a glance

Intelligence
2
Speed
—
Latency
—
Input price
Not published
Output price
Not published
Context window
130Ktokens
Parameters
1.6billions

Summary

Comparison summary

Granite 4.0 1B scores 2 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 3).

Specifications

Technical specifications

Model nameGranite 4.0 1B
ProviderIBM
Release dateOctober 28, 2025
Intelligence score2
Speed—
Latency (TTFT)—
Input priceNot published
Output priceNot published
Context window130,000 tokens
Parameters1.6B
ReasoningNo
Input modalitiestext
Output modalities—
Open weightsYes
LicenseApache 2
API availability—
SourceModel Intelligence legacy profile: granite-4-0-nano-1b

FAQ · 15

Frequently asked questions

Granite 4.0 1B was released on October 28, 2025.

Granite 4.0 1B was created by IBM.

Granite 4.0 1B scores 2 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 3).

No, Granite 4.0 1B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Granite 4.0 1B supports text input.

Granite 4.0 1B supports text output.

No, Granite 4.0 1B does not support image input. It can only process text.

No, Granite 4.0 1B is not multimodal. It only supports text input.

Granite 4.0 1B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Granite 4.0 1B is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Granite 4.0 1B has 1.6 billion parameters.

Granite 4.0 1B is released under the Apache 2.0 license. This license allows commercial use.

Granite 4.0 1B achieves a score of 2 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Granite 4.0 1B is an open weights model that can be self-hosted.

Granite 4.0 1B is an open weights model that can be downloaded and self-hosted.