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.

⬇ 766.0K HF downloads♥ 2007 likesgoogle/gemma-3-27b-it· stats from 8/14/2026

Consumer GPUPro GPU

131K

Max Context

3

Quant Variants

GGUF Q4_K_M

Best Quality

97.2%

Accuracy Retained

Calculate VRAM Hugging Face Compare

Quantization Variants

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

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

Format	Level	BPW	VRAM	PPL Loss	Speed	Source	Actions
GGUF	Q4_K_M	4.85	16.2 GB	2.8%	48 tok/s	Community	Calc HF
GGUF	Q3_K_M	3.87	13.0 GB	5.5%	55 tok/s	Estimated	Calc HF
AWQ	INT4	4	14.5 GB	3.8%	62 tok/s	Estimated	Calc HF

Similar models

Compare with Gemma 3

Gemma 3 4B IT

Google Gemma 3

Consumer GPUMac / Apple Silicon

3.0 GBmin VRAM·99.8%accuracy

Google Gemma 3 multimodal 4B. 128K context; strong vision + text on 8GB cards.

Gemma 3 12B IT

Google Gemma 3

Consumer GPUMac / Apple Silicon

8.0 GBmin VRAM·98.7%accuracy

Mid-size Gemma 3 with vision. Fits 16GB at Q4; excellent multilingual chat.

Qwen3-VL 30B-A3B Instruct

Alibaba Qwen3-VL

Consumer GPUPro GPU

15.2 GBmin VRAM·99.7%accuracy

Multimodal MoE with only ~3B active parameters, so it stays responsive on Apple unified memory and survives CPU offload far better than a dense 30B. Q4 ~19GB — a 24GB card holds it outright.

Magistral Small 1.2 24B

Mistral Magistral

Consumer GPUMac / Apple Silicon

13.0 GBmin VRAM·99.4%accuracy

Mistral's reasoning model on a Mistral Small 3.2 base, with reasoning wrapped in [THINK] tags. Q4 ~14GB puts explicit chain-of-thought on a 16GB card — the level below the 70B-class reasoners most guides assume.

How to actually run this

Deployment guides for this model and this class of hardware.