NelsaHost
search Login
smart_toy
Phi Large Language Models

Phi-3 Medium 14B (14.00B)

Parameters
14.00B
VRAM (FP16)
28.0GB
VRAM (INT4)
7.0GB
Context
128000
check_circle View Compatible GPUs open_in_new View on HuggingFace

tune Quantization Options

Quantization VRAM Required Min GPU
FP16 (Half Precision) 28.0GB A6000 / 2x 4090
INT8 (8-bit Integer) 14.0GB RTX 4080
Q4_K_M (GGUF 4-bit) 7.0GB RTX 3070 / 4060
q3_k_m 5.6GB RTX 3070 / 4060

memory Compatible GPUs

check_circle

RTX 4090

24.0GB VRAM

Perfect
check_circle

RTX 4090

24.0GB VRAM

Perfect
check_circle

RTX 4090

24.0GB VRAM

Perfect
check_circle

RTX 3090 Ti

24.0GB VRAM

Perfect
check_circle

RTX 3090 Ti

24.0GB VRAM

Perfect
check_circle

RTX 3090 Ti

24.0GB VRAM

Perfect
View All Compatible GPUs

Model Details

Family Phi
Category Large Language Models
Parameters 14.00B
Context Length 128000

Similar Models

Phi-3 Mini 3.8B 3.80B Phi-3 Small 7B 7.00B