Back to Calculator
Gemma 4 31B
HotGoogle's flagship dense Gemma 4 model, #3 open model on Arena AI, multimodal (text/image/video), 256K context, built-in reasoning
Model Specifications
ArchitectureVISION
Parameters31B
Familygemma
VRAM (Q4)15.5GB
Dense architecture. 256K context. LMArena score 1452. Apache 2.0
Share this Model
Send this model's specs directly to your community.
Similar Models
Related Guides
How much VRAM do you really need?
A complete breakdown of quantization levels and VRAM overhead for running local models.
Best GPUs for Machine Learning in 2026
Comparing NVIDIA and AMD options for the best speed-to-dollar ratio.
GGUF vs EXL2 vs AWQ
Understanding local AI formats and which one to pick for your specific hardware.