NelsaHost

Hardware AI Models Compatibility Compare

search Login

smart_toy

Gemma Large Language Models

Gemma 2 2B (2.00B)

Parameters

2.00B

VRAM (FP16)

4.0GB

VRAM (INT4)

1.0GB

Context

8192

check_circle View Compatible GPUs open_in_new View on HuggingFace

tune Quantization Options

Quantization	VRAM Required	Min GPU
FP16 (Half Precision)	4.0GB	RTX 3070 / 4060
INT8 (8-bit Integer)	2.0GB	RTX 3070 / 4060
Q4_K_M (GGUF 4-bit)	1.0GB	RTX 3070 / 4060
q3_k_m	0.8GB	RTX 3070 / 4060

memory Compatible GPUs

RX 7900 XTX

24.0GB VRAM

RX 7900 XTX

24.0GB VRAM

RX 7900 XTX

24.0GB VRAM

RX 7900 XTX

24.0GB VRAM

RTX 4090

24.0GB VRAM

RTX 4090

24.0GB VRAM

View All Compatible GPUs

Model Details

Family Gemma

Category Large Language Models

Parameters 2.00B

Context Length 8192

Similar Models

Gemma 2 27B 27.00B Gemma 2 9B 9.00B