Granite 3.0 — local AI model by IBM

Written by Jakub Rusinowski · Last updated

Superseded model. Granite 3.0 has been superseded by IBM Granite 4.0. This page is kept for reference; the newer family is a better starting point. View IBM Granite 4.0 →

IBM's enterprise-grade model family. Granite 3.0 is Apache 2.0 licensed and rigorously trained for coding, transparency, and safety in business environments.

IBM Research Hugging Face

Variants

The smallest Granite 3.0 variant needs about 6 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache.

ModelVRAM
Granite 3.0 8B Instruct →
8B
~5.6 GB

Memory is quantized weights plus overhead at Q4_K_M, from the same engine as the GPU & VRAM checker.

How to run Granite 3.0 locally

Install Ollama, then pull the tag.

ollama run granite3-dense

Pick a size above for its own VRAM figure, speed estimate and install command.

Licence

Apache-2.0Commercial use permitted

Commercial use permitted. No usage restrictions beyond attribution.

Applies to: Granite 3.0 8B Instruct

Recommended GPU

The cheapest catalogued GPU that runs Granite 3.0 locally (min 6 GB VRAM) is the Intel Arc B570 (10 GB).

Affiliate disclosure: Some links on this page are affiliate links — if you buy through them, LLM Configurator may earn a commission at no extra cost to you. As an Amazon Associate, LLM Configurator earns from qualifying purchases.
Intel Arc B570 10GB
10 GB VRAM · 150 W board power
2026 prices are volatile — check the current listing.

Can I run Granite 3.0 on my GPU?

Granite 3.0 — frequently asked questions

How much VRAM does Granite 3.0 need?

Granite 3.0 needs about 6 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Granite 3.0 8B Instruct (6 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run Granite 3.0 on an RTX 4090 (24 GB)?

Yes — Granite 3.0 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.

What quantization should I use for Granite 3.0?

Q4_K_M is the best balance of quality and VRAM for Granite 3.0 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.

How do I run Granite 3.0 with Ollama?

Install Ollama, then run: ollama run granite3-dense. This downloads Granite 3.0 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.