Can Gemma 3 12B run locally?

Yes, the weights are open and available on Hugging Face. You can run it with Ollama or LM Studio; check your VRAM against the quantisation you plan to use, as a 12B model at full precision is demanding.

What does Gemma 3 12B cost via API?

Pricing is $0.05 per million input tokens and $0.15 per million output tokens, which puts it at the very cheap end of hosted models. The context window is 131,072 tokens.

How does Gemma 3 12B differ from Gemma 3 27B?

The 27B is the largest model in the Gemma 3 family and will generally outperform the 12B on complex reasoning and harder tasks; the 12B trades some of that capability for lower hardware requirements and lower API cost.

Gemma 3 12B

5217°

#llm #google #vision #multilingual #chat #local

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Google | 131,072 token context | $0.05/M input, $0.15/M output. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after Gemma 3 27B

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Gemma 3 12B is Google's open-weights multimodal model that takes both images and text as input and returns text. At this size it sits between the smaller Gemma 3 models and the 27B flagship, offering a 128k context window, support for over 140 languages, and function calling at a price that barely registers. It suits developers and researchers who want a capable vision-language model they can run locally or call cheaply via API.

Known for

Vision-language input: attach an image and ask questions about it
128k token context window for long documents
Function calling and structured output support built in
Over 140 languages understood
Open weights: download and run it yourself

Watch out for

Output only text; it cannot generate images or audio.
Gemma licences carry usage restrictions — check Google's terms before commercial deployment.
The 27B sibling will outperform it on harder reasoning tasks if you have the hardware.

Best for

Prompts to try

Read a receipt or invoice

Attach a photo of a receipt or invoice. List every line item, its quantity and price in a markdown table, then give the total. If any figure is hard to read, flag it with a question mark rather than guessing.

Multilingual document summary

Here is a document written in a language other than English. Identify the language, summarise the main points in English in three bullet points, then translate the opening paragraph into English as faithfully as you can.

Function-calling schema

I need a JSON schema for a function called search_products that accepts a string query, an optional integer max_results defaulting to 10, and an optional array of strings called categories. Return only the JSON schema object, no explanation.

Compare with

Gemini 2.5 Flash Lite
API-only model
1,048,576 token context · $0.10/M input, $0.40/M output
Gemini 3.1 Flash Lite
API-only model
1,048,576 token context · $0.25/M input, $1.50/M output
Gemini 3.5 Flash Lite
API-only model
1,048,576 token context · $0.30/M input, $2.50/M output
Nano Banana (Gemini 2.5 Flash Image)
API-only model
32,768 token context · $0.30/M input, $2.50/M output

More text models from google

Questions people ask

Can Gemma 3 12B run locally?: Yes, the weights are open and available on Hugging Face. You can run it with Ollama or LM Studio; check your VRAM against the quantisation you plan to use, as a 12B model at full precision is demanding.
What does Gemma 3 12B cost via API?: Pricing is $0.05 per million input tokens and $0.15 per million output tokens, which puts it at the very cheap end of hosted models. The context window is 131,072 tokens.
How does Gemma 3 12B differ from Gemma 3 27B?: The 27B is the largest model in the Gemma 3 family and will generally outperform the 12B on complex reasoning and harder tasks; the 12B trades some of that capability for lower hardware requirements and lower API cost.

Captain's verdict
A genuinely cheap, locally-runnable vision-language model that covers 140-plus languages — hard to argue with at this price.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

Gemma 3 12B is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm google vision multilingual chat local budget

Browse by Model Family