Gemma 2 27B Instruct

27B

Google Gemma 2

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

⬇ 4.6K HF downloads♥ 174 likesbartowski/gemma-2-27b-it-GGUF· stats from 8/8/2026
Consumer GPUPro GPU

8K

Max Context

3

Quant Variants

GGUF Q5_K_M

Best Quality

98.7%

Accuracy Retained

Calculate VRAMHugging FaceCompare

Quantization Variants

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

Measured = site benchmarks · Estimated = formula · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M4.8518.5 GB2.9%48 tok/sEstimated
CalcHF
GGUFQ5_K_M5.6821.2 GB1.3%42 tok/sEstimated
CalcHF
AWQINT4416.2 GB4.0%58 tok/sEstimated
CalcHF

Similar models

Compare with Gemma 2
9B

Gemma 2 9B Instruct

Google Gemma 2

Consumer GPUMac / Apple Silicon
5.8 GBmin VRAM·99.8%accuracy

Google's compact Gemma 2 with sliding window attention. Punches above 9B.

2B

Gemma 2 2B Instruct

Google Gemma 2

Consumer GPUMac / Apple Silicon
1.8 GBmin VRAM·99.7%accuracy

Ultra-compact Gemma 2. Runs on 4GB VRAM; great for edge prototyping.

32B

Qwen2.5 32B Instruct

Alibaba Qwen2.5

Consumer GPUPro GPU
16.4 GBmin VRAM·97.3%accuracy

Near-GPT-4 reasoning on a 24GB VRAM card (Q4_K_S). Groundbreaking value.

24B

Mistral Small 24B Instruct

Mistral AI

Consumer GPUPro GPU
13.5 GBmin VRAM·97.8%accuracy

Mistral's efficient 24B. Strong multilingual; fits on 24GB with Q4.