← All modelsMODEL CHECK

Can I run Llama 4 Scout?

Llama 4 Scout by Meta needs around 96 GB of RAM at the recommended 4-bit quantization (66.1 GB download). Your hardware is checked below — instantly, nothing leaves your browser.

Reading your hardware signals…

Specifications

Parameters109B (17B active)
Context window10M tokens
ProviderMeta
LicenseLlama Community
Released2025-04
Best forChat, Vision

Size by quantization

QuantizationBits/weightDownloadMin RAMQuality
Q2_K3.3545.6 GB64 GBNoticeable loss
Q4_K_MRecommended4.8566.1 GB96 GBRecommended
Q5_K_M5.6577.0 GB128 GBHigh
Q8_08.5115.8 GB192 GBNear-original
F1616218.0 GB256 GBOriginal

Sizes are estimates from parameter count × bits per weight; real GGUF builds vary slightly.

Run it locally

The easiest path is Ollama — one command and you're chatting:

ollama run llama4:scout

Frequently asked questions

Llama 4 Scout System Requirements — Can I Run It Locally?