runlocal.devCheck My GPU →

Gemma 4 26B-A4B

MoEGemma

Gemma 4 MoE variant with 4B active params from a 26B pool. Unsloth achieved best-in-class GGUF across 22 quantization levels — broadest quant coverage in the Gemma 4 family.

Provider

Google DeepMind

Parameters

26B (4B active MoE)

Context

128K

Released

2026-04-20

VRAM Requirements by Quantization

MethodDisk SizeVRAM RequiredFits GPUs
Q8_027 GB29 GB5 GPUs
Q4_K_M15 GB16.5 GB9 GPUs
Q4_014.3 GB15.5 GB9 GPUs
Q2_K9 GB10.5 GB18 GPUs

Install with Ollama

Run in terminal:

ollama pull gemma4:26b-a4b

Minimum 10.5GB VRAM required. Install Ollama from ollama.com

Benchmark Scores

mmlu83%
humaneval80.5%

Scores are approximate and may vary by quantization level.

Compatible GPUs (18)

HuggingFace

google/gemma-4-26b-a4b-it

View on HF →