google

Google: Gemma 3 12B

The Google model known as Gemma 3 12B is a large language model that can process both text and image inputs. It has a high context length of 131,072 tokens, allowing it to handle complex tasks with extended dialogue or text sequences. The model also supports tools, indicating it can be integrated into various workflows, but lacks reasoning capabilities and does not provide structured output. Those on a budget may want to consider shortlisting this model due to its relatively low price point of $0.05 per million input tokens. However, its performance is mixed, with a blended benchmark score of 1.6 across three independent benchmarks, which may be lower than what some users require for their specific tasks. Its strengths in handling long text sequences and supporting tool integration could make it a suitable option for certain applications, but its limitations in reasoning and structured output should also be considered.

Open weights 12.2B parameters, about 6.8 GiB at Q4_K_M: fits comfortably on 16 of 17 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
91/100
price + capability + benchmarks
Input Price
$0.05
per 1M tokens · checked 2026-09-07
Output Price
$0.15
per 1M tokens · checked 2026-09-07
Context Window
131,072
tokens

Benchmark results

Independent, published benchmarks. Blended score 1.6 across 3 benchmarks, last refreshed 2026-09-07. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 1.6
AI Index Coding software engineering tasks 9.5
AI Index Agentic multi-step tool-using tasks 0.2
Model ID
google/gemma-3-12b-it
Vendor
google
Released
March 2025
Tokenizer
Gemini
Input Modalities
text, image
Output Modalities
text
Max Output
16,384 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.05/M input and $0.15/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.03
A month of a busy support chatbot 5M in / 2M out $0.55

Similar models

Quick answers

How much does Google: Gemma 3 12B cost?
$0.05 per million input tokens and $0.15 per million output tokens.
What is Google: Gemma 3 12B's context window?
131,072 tokens, roughly 196 pages of text in a single request.
Does Google: Gemma 3 12B support tool calling?
It supports tool calling, structured output.
Can Google: Gemma 3 12B process images?
Yes, it accepts image input.