Gemma 4
Google·
LLMsopen-weightEdge / Consumer
Overview
Google's strongest open-weight model family. Apache 2.0 license. Available in multiple sizes including on-device variants (E2B, E4B) and a 31B dense model for self-hosted deployments. Frontier-competitive on reasoning and coding benchmarks.
Capabilities and innovations
31B dense flagshipOn-device variants (2B, 4B)Apache 2.0 licenseFrontier-competitive reasoning and codingMulti-size open-weight familyOn-device optimized variantsApache 2.0 frontier model
Benchmarks
No benchmark values are recorded for this model.
Architecture and hardware
- Parameters
- 31B total (Dense)
- Estimated VRAM at Q4
- ~18 GB, Edge / Consumer class
- Quantization formats
- GGUF, BF16
- Recommended runtime
- Ollama
- License
- Apache 2.0
Links
More from Google
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.