ModelDen

Granite 3.3 8B Instruct

8B · Q4_K_M · ~4.8 GB
Released April 16, 2025

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.

Coding90
HumanEval · source · as of 2026-06
Math & logic81
AIME 2024 · source · as of 2026-06
General58
Arena Hard · source · as of 2026-06

Granite 3.3 models feature enhanced reasoning capabilities and support for Fill-in-the-Middle (FI…

About this model

Context window
32,768 tokens
Will Granite 3.3 8B 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 →