
Granite 3.0 2B Instruct
IBM's 2B instruction-tuned enterprise LLM with 12-language support, Apache 2.0.
About
Granite 3.0 2B Instruct is IBM's 2-billion-parameter instruction-tuned language model, released on October 21, 2024 as part of the Granite 3.0 family. It is fine-tuned from Granite-3.0-2B-Base with supervised finetuning, RL alignment, and model merging, trained on over 12 trillion tokens across 12 natural languages and 116 programming languages.
The model supports summarization, classification, extraction, question answering, RAG, code tasks, and function calling. Unusually for its size class, IBM released the entire Granite 3.0 family under the permissive Apache 2.0 license with published training-data disclosures.
The 2B instruct variant targets efficient enterprise deployment, including edge and local use via Ollama, Replicate, watsonx, and NVIDIA NIM.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 8/10
Scored 8/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 111; Trending score 80/100 from researcher assessment.