Gemma 3 27B IT

27B

Google Gemma 3

Gemma 3 large instruct with long context and multimodal support. Q4 ~16GB — dual-GPU or 24GB card with short ctx.

841.6K HF downloads2003 likesgoogle/gemma-3-27b-it· stats from 7/27/2026
Consumer GPUPro GPU

131K

Max Context

3

Quant Variants

GGUF Q4_K_M

Best Quality

97.2%

Accuracy Retained

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_M4.8516.2 GB2.8%48 tok/sCommunity
CalcHF
GGUFQ3_K_M3.8713.0 GB5.5%55 tok/sEstimated
CalcHF
AWQINT4414.5 GB3.8%62 tok/sEstimated
CalcHF

Similar models

Compare with Gemma 3