Gemma 4 12B IT
Gemma 4 12B IT is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.
Use it for
- Teams evaluating coding, rag, and agents
- Workloads that can use a 256k context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- Workloads where another current model has stronger sourced task evidence
- 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
- Fine-tuned
Cheapest of 2 routes · Hugging Face Inference Endpoints
About
Instruction-tuned version of Gemma 4 12B. Open weight (Apache 2.0), 12B parameters, encoder-free multimodal (text, image, audio). Optimized for chat and instruction-following. Runs on a 16GB laptop.
Top use-case fit: coding, agents, and build tasks
Coding
1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 2Compare API pricing across 2 providers 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
Benchmark peer barsfor Coding
Benchmark scores(4)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| Google-Proof Q&A | 78.8 | DiamondObserved 2026-06-03 | — | Source |
| MMLU PRO | 77.2 | MMLU ProObserved 2026-06-03 | — | Source |
| LiveCodeBench | 72.0 | v6 pass@1Observed 2026-06-03 | — | Source |
| AIME 2026 | 77.5 | no tools / no calculatorObserved 2026-06-03 | — | Source |
Migration checks
No linked migration route is available for this model yet.
Cheapest of 2 routes · Hugging Face Inference Endpoints