LLM ReferenceLLM Reference

Granite 4.0 Micro

granite-4.0-micro

Open Source

About

IBM Granite 4.0 Micro is a 3B dense (non-hybrid) instruct model using a conventional transformer architecture. 40 attention layers with GQA (32 heads, 8 KV heads) and RoPE. Distinct from Granite 4.0 H-Micro which uses hybrid Mamba2/attention architecture. Supports multilingual dialog (12 languages), code (FIM), tool-calling, and RAG. Apache 2.0.

Granite 4.0 Micro has a 128K-token context window.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Rankings

Best Open Source LLMsBest Small Language Models (SLMs)Cheapest LLM APIsBest LLM APIsBest Free LLMsBest LLMs for WritingBest LLMs for Marketing

Specifications

FamilyGranite 4
Released2025-10-02
Parameters3B
Context128K
ArchitectureDense decoder-only transformer: 40 layers, GQA with RoPE, SwiGLU

Created by

IBM ResearchIBM Research

Creating reliable and adaptable AI solutions

Armonk, New York, United States
Founded 1945
Website