Skip to content
AI Stack Nest
Open weightschat

Llama 3.1 70B

Workstations or servers with a lot of memory

Specifications

Llama 3.1 70B specifications
PropertyValue
MakerMeta
FamilyLlama
Parameters70B
Context window128K
LicenseLlama 3.1 Community License
Commercial useAllowed under the Meta license terms; read them
Best forWorkstations or servers with a lot of memory
Last verified17 Nov 2026

Memory needed to run Llama 3.1 70B

Memory by precision
PrecisionMemory (GB)
Ollama default download44.5 GB

Check your own computer with the will-it-run checker.

What it is

This is the 70 billion parameter size of Meta's Llama 3.1 family, with a 128K token context window according to the Ollama library.

Size on disk

The Ollama page lists the download at about 43 GB. You need at least that much free disk space and enough memory to hold the model while it runs, so it is aimed at workstations and servers rather than everyday laptops.

How to run it

Run ollama run llama3.1:70b. Check the license terms on the model card before using it commercially.

About these notes

Sizes, context length and license were read from the Ollama library page and the Hugging Face model card on 2026-11-17. We have not benchmarked this model ourselves, so we give no speed or quality scores.

More models

Official source: model card. Figures come from the vendor and our own tests; always confirm on the model card before building on a model.