Gemma 4 12B
Released
2026-06-03
Last refreshed
2026-10-07
Status
Researched 127d ago
Open sourceCommercial use: permittedMultimodalRAGAgentsLong contextVisionJSON / Tool useopen-sourcemultimodal
Google DeepMind releases · 52 in the last 12 months · this family litChangelog →
Specifications
- Family
- Gemma 4
- Released
- 2026-06-03
- Context
- 256K
- Parameters
- 12B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2025-01
- Specialization
- general
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
Created by
Pricing
Output / 1M
-
Input / 1M
-
Cheapest of 2 routes · Hugging Face Inference Endpoints
Links
About
Google DeepMind's 12B open-weight multimodal model (Apache 2.0), designed to run on a 16GB laptop. First medium-sized model with native audio ingestion alongside text and image. Unified encoder-free decoder-only architecture. Supports 140+ languages. MMLU Pro: 77.2%.
Providers(2)
Compare all 2Compare API pricing across 2 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Hugging Face Inference Endpoints | - | - | Partial |
| Kaggle Models | - | - | Partial |
Capabilities
VisionMultimodalReasoningJSON / Tool useStructured OutputsAudio
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
Rankings & picks(1)
Compare Gemma 4 12B with other models
Comparison and alternatives
Browse all comparisons →Created by
Pricing
Output / 1M
-
Input / 1M
-
Cheapest of 2 routes · Hugging Face Inference Endpoints
Links