A model is the software that produces AI answers. This guide compares models and tools. New to this? Choose a setup path first. Use the lists below when you want more detail.

New words, in plain language

Local / cloud: Local runs on your computer. Cloud runs on computers managed online.
Model / tokens: A model produces AI answers. Tokens are small pieces of text; some services charge for the tokens used.
Account / identity: An account is a sign-in. Your cloud identity is the account you use for online services.
Connector / permissions: A connector links an AI tool to another service. Permissions are the access you allow.

Field Guide · Week of 5 October 2026

Gemma 4 31B

Google · United States · Google

Google’s dense 31B. One brain, no mixture. Apache. It needs a 32 GB machine and will not fit a 16 GB laptop.

Where it runs: Runs on your computer
Memory: 24–32 GB (4-bit)
Size: 31B dense
License: Apache 2.0
Hugging Face downloads: 9.9M
Hugging Face likes: 4k
Card last updated: 20 July 2026

On your computer · #2 United States · #2

Why it is on this week’s list

The official card was missing from the guide. Downloads put it second on a computer this week, behind the 26B mixture.

Use it when

A 24 GB+ machine and you want the dense Gemma, not the mixture.

Skip it when

16 GB or less — take 12B or gpt-oss 20B.

Walk me through installing this Hugging Face card All lists