Monday, October 26, 2026 · Edition updated 6:00 AM ETMON, OCT 26 editionNext edition in Next in --:--:--
Intelligence Verdict
Compare AI models

Gemma 4 26B A4B vs Gemma 4 31B

Google's Gemma 4 26B A4B and Google's Gemma 4 31B, side by side: what each costs, how much it can read at once, whether you can run it yourself, and where independent tests place it.

  • —no price to compare
  • 256Kcontext window, both
  • 0–0higher placings on boards ranking both
In short

How they differ.

Worked out from the figures below. Prices and specs are the makers' own, read Oct 20, 2026.

  • Both can be downloaded and run on your own machine.
  • No independent board we follow ranks both models yet.
Side by side

The specs.

Gemma 4 26B A4BGemma 4 31B
Made byGoogle · USGoogle · US
ReleasedApr 2, 2026Apr 2, 2026
Price per 1M tokensFree to download; hosts set pricesFree to download; hosts set prices
Context window256K256K
Takes intext, image, videotext, image, video
Download and run it yourselfYes (Apache 2.0)Yes (Apache 2.0)
Size25.2B parameters, 3.8B active30.7B (dense) parameters
Maker says“Today, we are introducing Gemma 4 — our most intelligent open models to date.”“Today, we are introducing Gemma 4 — our most intelligent open models to date.”
SourcesPrices, Oct 20, 2026 · DescriptionPrices, Oct 20, 2026 · Description
Independent tests

Where they place.

None of the boards we follow lists either model yet.