LLM Reference

Granite 4.0 Micro

Released
2025-10-02
Last refreshed
2026-04-29
Status
Researched 45d ago
Open SourceCommercial use allowedLong context

Granite 4.0 Micro has model metadata, but missing tracked provider pricing keeps it from being a default production pick.

Use it for

  • Teams evaluating long context
  • Workloads that can use a 128k context window

Do not use it for

  • Cost-sensitive launches that need sourced token pricing
  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
Granite 4
Released
2025-10-02
Context
128k
Parameters
3B
Architecture
Dense decoder-only transformer: 40 layers, GQA with RoPE, SwiGLU
Openness
Open source
License
Apache 2.0(OSI)Commercial use allowed
Created by

Creating reliable and adaptable AI solutions

Armonk, New York, United States
Founded 1945
Website
Pricing

No tracked provider token pricing is available yet.

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 is an open-source model in the Granite 4 family. The structured metadata tracks a 128k-token context window. No headline benchmark score is tracked for Granite 4.0 Micro yet.

Top use-case fit

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Long context

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.