runlocal.devCheck My GPU →

Gemma 4 31B

Apache 2.0

Google's flagship dense 31B model with 256K context. Near-frontier quality, top open-source performer on code and reasoning. Arena Elo ~1452.

Provider

Google

Parameters

31B

Context

262.144K

Released

2026-04-08

VRAM Requirements by Quantization

MethodDisk SizeVRAM RequiredFits GPUs
Q8_031 GB34 GB2 GPUs
Q4_K_M17 GB19 GB7 GPUs
Q4_015.5 GB17.5 GB7 GPUs
Q2_K9.5 GB11 GB14 GPUs

Install with Ollama

Run in terminal:

ollama pull gemma4:31b

Minimum 11GB VRAM required. Install Ollama from ollama.com

Benchmark Scores

mmlu89%
humaneval82%

Scores are approximate and may vary by quantization level.

Compatible GPUs (14)

HuggingFace

google/gemma-4-31b-it

View on HF →