Llama 3.2 3B Instruct

Meta · 3.2B · Q4_K_M · ~1.9 GB

Released September 25, 2024

How good is it? — per-capability quality

Each number is the model’s score on its best public benchmarkfor that skill — named and linked below, never a blend. Scores compare cleanly when the benchmark matches; benchmarks are gameable, so we show the receipts rather than hide behind one number.

Coding—

Not yet scored on a benchmark we can cite — left blank rather than guessed.

Math & logic48

MATH · source · as of 2026-06

General33

GPQA · source · as of 2026-06

Llama 3.2 3B Instruct is a large language model that supports a context length of 128K tokens and…

About this model

Developer: Meta
Family: Llama 3.2
License: Llama Community License
Context window: 32,768 tokens

Developer site ↗

Will Llama 3.2 3B Instruct actually run on YOUR graphics card?

This page shows fit for a generic VRAM tier. Tell us your GPU for a personalized speed estimate and fit verdict.

Enter your graphics card →