Gemma 3 12B

Mar 2025
Gemma 3 12B
Compare in
on
—per task?
$0.05 / $0.10per 1M in / out?
—output speed?
131Kcontext

Rankingin non-thinking mode?

Run it yourself

estimate
Fits on✓ 8 GB (phone, laptop) · compressed✓ 16 GB · 8-bit✓ 24 GB GPU · 8-bit✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceGemma termscommercial use with conditions

FAQ

How much does Gemma 3 12B cost?›

$0.05 per 1M input tokens and $0.10 per 1M output tokens (cheapest host: Novita).

Is Gemma 3 12B free to use?›

There is no free API; the cheapest paid price is $0.05 per 1M input tokens. The weights are open, so you can run it yourself.

How good is Gemma 3 12B, and what is it best at?›

#318 of 360 in Chat & Knowledge, #134 of 138 in Agents & Tool Use, #111 of 197 in Writing & Language, #126 of 132 in Vision & Documents.

Is Gemma 3 12B better than Llama 3.2 90B?›

On MMMU · validation, Gemma 3 12B scores 59.6 vs 60.3 — about the same.

How can I use Gemma 3 12B?›

Through the API of AWS Bedrock, DeepInfra, NextBit, Novita.

What is the context window of Gemma 3 12B?›

131K tokens, with up to 16K output tokens.

When was Gemma 3 12B released? Is there a newer version?›

Released 2025-03-01. It is the current version in its line.

Is Gemma 3 12B open source?›

Yes, the weights are open (gemma licence).

Can I run Gemma 3 12B locally?›

The weights are open and can be self-hosted; hardware needs are not confirmed yet.

Can Gemma 3 12B read images?›

It accepts text and images as input.

What is Gemma 3 12B?›

Gemma 3 12B is an open-weights language model from Google, released Mar 2025.

What are the best alternatives to Gemma 3 12B?›

GPT-5.1 (better), MiMo VL 7B RL (open weights).