Google

gemma-3-12b-it

SIZE12B

32Quality

Vision

Downloads370K/mo

Likes870

Vision-language model from Google, 12B parameters.

Open weightsGemma license505/1040

Drag to turn

GoogleTextPromo

gemma-3-12b-it

Vision-language model from Google, 12B parameters.

google/gemma-3-12b-it

Type: Text
Quality: 32 · Top 68% on the Epoch Capabilities Index
Parameters: 12B (12,187,325,040)
Downloads: 370K in the last 30 days
Likes: 870
Access to weights: Accept the license on Hugging Face first
On Hugging Face since: Mar 1, 2025
Takes in: Text, Image
Puts out: Text
Access: Open weights
License: Gemma license
Rarity: Promo
Set number: 505/1040

Open on Hugging Face Quality 32 Where to run it 14 Evolution 2/4 Race it 68 tok/s Meet its creature Battle DeepSeek V4 Pro

License read from the model’s Hugging Face card. Stats from Google’s official Hugging Face account, refreshed daily.

How good is it?

Public leaderboard scores for gemma-3-12b-it, refreshed daily from Epoch AI and LMArena.

Top 68% of the 277 models on the Epoch Capabilities Index: #189.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#189 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.123.5 index
Listed as Gemma 3 12B
LMArena Text#221 of 416
People compare two anonymous answers and vote for the better one.1,334 rating
LMArena Text · Coding#274 of 411
The text arena’s coding prompts only.1,281 rating
LMArena Text · Math#231 of 400
The text arena’s math prompts only.1,307 rating
LMArena Text · Creative writing#189 of 414
The text arena’s creative writing prompts only.1,331 rating

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

12 providers sell gemma-3-12b-it through an API, and 2 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestHelicone$0.05 in · $0.10 out
Free to try1 providerNvidia
Fastest on Hugging FaceDeepInfra68 tokens/s

API providers

Provider	Input	Output	Context
NvidiaFree`google/gemma-3-12b-it`	Free	Free	131K
HeliconeCheapest paid`gemma-3-12b-it`	$0.05	$0.10	131K
Novita AI`google/gemma-3-12b-it`	$0.05	$0.10	131K
Kilo Gateway`google/gemma-3-12b-it`	$0.04	$0.12	131K
Deep Infra`google/gemma-3-12b-it`	$0.05	$0.15	131K
Eden AI`deepinfra/google/gemma-3-12b-it`	$0.05	$0.15	131K
OpenRouter`google/gemma-3-12b-it`	$0.05	$0.15	131K
AI/ML API`google/gemma-3-12b-it`	$0.069	$0.21	131K
NanoGPT`unsloth/gemma-3-12b-it`	$0.27	$0.27	131K
Amazon Bedrock`google.gemma-3-12b-it`	$0.09	$0.29	131K

Show 2 more providers

Provider	Input	Output	Context
Merge Gateway`google/gemma-3-12b-it`	$0.09	$0.29	128K
Neon`gemma-3-12b`	$0.15	$0.50	131K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraFastestTools	$0.05	$0.15	131K	68 tok/s	0.3s
Featherless	—	—	—	—	—

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

gemma-3-12b-it

gemma-3-12b-it

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Where to run it

API providers

Hugging Face Inference Providers

More from Google

Gemini 4 Argon

embeddinggemma-2

Gemini 3.8 Flash

timesfm-3.0-pytorch

Gemini 3.7 Flash

Gemini 3.6 Flash

Gemini 3.5 Flash Lite

Nano Banana 2 Lite