Gemma 3 12B
Gemma 3 12BRankingconfiguration unstated?
Alternatives?
CheaperGemma 3 4BunstatedOpenwins 42%-32%$0.04 / $0.05
BetterGPT-6 Lunamaxwins 61%+220%$0.068Function calling only with none · Chat Completions+3OpenGemma 4 26B A4Bunstatedwins 59%+320%$0.15 / $0.60Memory (4-bit): 6.1 GB → 15 GBBetterGPT-5.6 Lunaxhighwins 61%+620%$0.085BetterGPT-5.6 Terraxhighwins 63%+7,100%$0.63Prompts with >272K input tokensGemma 3 4BunstatedOpenwins 42%-32%$0.04 / $0.05GPT-6 Lunamaxwins 61%+220%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 61%+620%$0.085GPT-5.6 Terraxhighwins 63%+7,100%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 67%+6,300%$0.72Remove unsupported parameters+5GPT-6 Solmaxwins 65%+6,300%$1.04Gemma 4 26B A4BunstatedOpenwins 59%+320%$0.15 / $0.60Memory (4-bit): 6.1 GB → 15 GB
Qwen3.8 27BunstatedOpenwins 55%+1,430%$0.42 / $2.55Memory (4-bit): 6.1 GB → 17 GB+5
Muse Glimmer 30BunstatedOpenwins 54%+700%$0.30 / $1.10Memory (4-bit): 6.1 GB → 18 GBQwen 3.5 27BunstatedOpenwins 54%+1,220%$0.30 / $2.40Memory (4-bit): 6.1 GB → 17 GBGemma 3 27BunstatedOpenwins 52%+60%$0.08 / $0.16Memory (4-bit): 6.1 GB → 16 GBGemini 4 Argonhighwins 74%—*$1.62Synchronous output stops at 65,536+2Gemini 3.8 Flashhighwins 71%—*$3.49Sampling parameters are ignored+1Gemini 3.1 Pro Previewunstatedwins 70%—$2 / $12Cannot use both thinking controlsGemini 3.6 Flashhighwins 69%—*$1.60Gemini 3 Flash Previewunstatedwins 67%—$0.50 / $3Gemini 2.5 Prounstatedwins 65%—$1.25 / $10Gemini 3.5 Flash Liteunstatedwins 64%—$0.30 / $2.50Gemma 4 31BunstatedOpenwins 62%—$0.10 / $0.34Memory (4-bit): 6.1 GB → 19 GBAll Google models →Run it yourself
estimateBenchmarks
all categoriesFAQ
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?›
#143 of 205 in Chat & Knowledge, #24 of 39 in Agents & Tool Use, #111 of 197 in Writing & Language, #24 of 41 in Vision & Documents.
Is Gemma 3 12B better than Command A?›
On Arena Text · creative writing, Gemma 3 12B scores 1,333 vs 1,336 — 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?›
Gemma 3 4B (cheaper), GPT-6 Luna (better), Gemma 4 26B A4B (open weights).