Gemma 2 27B Instruct

27B

Google Gemma 2

Largest open Gemma 2. Strong reasoning; needs 24GB+ VRAM at Q4.

⬇ 7.1K HF downloads♥ 174 likesbartowski/gemma-2-27b-it-GGUF· stats from 6/24/2026

Consumer GPUPro GPU

Max Context

Quant Variants

GGUF Q5_K_M

Best Quality

98.7%

Accuracy Retained

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Format	Level	BPW	VRAM	PPL Loss	Speed	Actions
GGUF	Q4_K_M	4.85	18.5 GB	2.9%	48 tok/s	Calc HF
GGUF	Q5_K_M	5.68	21.2 GB	1.3%	42 tok/s	Calc HF
AWQ	INT4	4	16.2 GB	4.0%	58 tok/s	Calc HF