Skip to content

Gemma 4 31B

Apache 2.0

Google · 31B · transformer-decoder

2026-04-02 262K context 31B params

Use Cases

chat code reasoning multilingual vision tools math writing summary

Quantization Options

QuantBitsVRAMQualityStatus
Q4_K_Mrec422.0 GBGood
Q8_0838.0 GBExcellent
F161666.0 GBExcellent

About this model

Gemma 4 31B is the flagship of the Gemma 4 family — a 30.7B dense model that ranks #3 on Arena AI among all open models, outcompeting models with 20x more parameters. It scores 84.3% on GPQA Diamond, 89.2% on AIME 2026, and 80.0% on LiveCodeBench. At Q4 it needs about 22 GB VRAM, fitting on a RTX 3090/4090/5090 or a Mac with 24 GB+ unified memory. Released under Apache 2.0, it's one of the most permissively licensed frontier-class open models available.

Benchmarks

85.2
mmlu_pro
84.3
gpqa_diamond
89.2
aime2026
80.0
livecodebench