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

DeepSeek V4 Flash

DeepSeek · China · DeepSeek

DeepSeek’s smaller V4. MIT license. Quantized, it can live on a strong laptop or a single workstation GPU.

Where it runs: Runs on your computer
Memory: 32–64 GB (quantized)
Size: 284B MoE · 13B active
License: MIT
Hugging Face downloads: 1M
Hugging Face likes: 2.3k
Card last updated: 22 June 2026

On your computer · #7 China · #6

Why it is on this week’s list

The reasoning quality people talk about, in a size that is no longer only a cluster.

Use it when

32 GB+ and hard problems — code, math, long chains.

Skip it when

16 GB. This will swap and feel broken.

Published scores

Scores as of 17 August 2026. A blank test is not a zero. We just will not invent it.

GPQA Diamond: 88.1
SWE-Bench Verified: 79.0
LiveCodeBench: 91.6
MMLU / MMLU-Pro: —
AIME: —
Humanity’s Last Exam: 32.1

What these numbers actually mean

Walk me through installing this Hugging Face card All lists