New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Gemma 4 12B
About Gemma 4 12B
Gemma 4 12B is an AI model developed by Google DeepMind, in the multimodal category, released in 2026, made available as an open-weights model with 12B params. Gemma 4 12B is a dense, unified encoder-free multimodal open model that natively ingests text, images, and audio by proj.
On this page you'll find Gemma 4 12B's full specifications, including a context window of 262.1K tokens, 4 benchmark results. Review provider pricing and benchmark scores below, or compare Gemma 4 12B head-to-head with other multimodal models.
Links
Run Gemma 4 12B locally — what to buy
Share this build ↗Sized to what Gemma 4 12B actually needs (~262k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.
Software support
✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.
Community
No reports yet. Own this model on some hardware? Be the first to confirm it runs.
No comments yet. Start the discussion.
Gemma 4 12B benchmark scores▶
| Benchmark | Category | Score | Variant |
|---|---|---|---|
| LiveCodeBench | code | 72% | |
| MMLU-Pro | general | 77.2% | |
| AIME 2026 | math | 77.5% | |
| GPQA Diamond | reasoning | 78.8% |
More models like Gemma 4 12B
Frequently asked questions
What is Gemma 4 12B? ▶
Gemma 4 12B is a dense, unified encoder-free multimodal open model that natively ingests text, images, and audio by proj It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.
Who created Gemma 4 12B? ▶
Gemma 4 12B was developed by Google DeepMind and released in 2026.
Is Gemma 4 12B open source or proprietary? ▶
Gemma 4 12B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.
What is Gemma 4 12B's context window? ▶
Gemma 4 12B supports a context window of 262.1K tokens, and has 12B params.
How much does Gemma 4 12B cost? ▶
Pricing for Gemma 4 12B depends on the provider. See the providers table on this page for the latest API rates.
How does Gemma 4 12B perform on benchmarks? ▶
Gemma 4 12B is benchmarked across 4 evaluations on GenAIList, including LiveCodeBench (72%). See the full benchmark table below and compare it with other models.
Know a great video about Gemma 4 12B?
Add YouTube Video
Add Tweet/Discussion
Report an Issue
Help us maintain accurate information in our database.
Suggest an Edit
Tell us what needs to be changed or corrected for