LLM Reference

Granite 3.1 2B Instruct

Released
2024-12-18
Last refreshed
2026-04-29
Status
Researched 45d ago
Open SourceCommercial use allowedLong context

Granite 3.1 2B Instruct 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 3
Released
2024-12-18
Context
128k
Parameters
2B
Architecture
Dense decoder-only transformer: 40 layers, 2048 embed, GQA 32/8 heads, RoPE, SwiGLU
Knowledge cutoff
2024-04
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 3.1 2B Instruct (2.5B actual parameters) is a compact instruction-tuned model with 128K context window. Dense decoder-only transformer with 40 layers, 2048 embedding, GQA. Trained on 12 trillion tokens. Supports 12 languages, code, RAG, and long-context tasks. Used as the LLM backbone for Granite Vision 3.2 2B. Apache 2.0.

Granite 3.1 2B Instruct is an open-source model in the Granite 3 family. The structured metadata tracks a 128k-token context window. No headline benchmark score is tracked for Granite 3.1 2B Instruct 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.