NelsaHost
search Login
smart_toy
Qwen Large Language Models

Qwen 2.5 72B (72.00B)

Parameters
72.00B
VRAM (FP16)
144.0GB
VRAM (INT4)
36.0GB
Context
131072
check_circle View Compatible GPUs open_in_new View on HuggingFace

tune Quantization Options

Quantization VRAM Required Min GPU
FP16 (Half Precision) 144.0GB A100 / H100
INT8 (8-bit Integer) 72.0GB A100 / H100
Q4_K_M (GGUF 4-bit) 36.0GB A6000 / 2x 4090
q3_k_m 28.8GB A6000 / 2x 4090

memory Compatible GPUs

check_circle

A100 40GB

40.0GB VRAM

Perfect
check_circle

A100 40GB

40.0GB VRAM

Perfect
check_circle

H100 SXM

80.0GB VRAM

Perfect
check_circle

H100 SXM

80.0GB VRAM

Perfect
check_circle

H100 SXM

80.0GB VRAM

Perfect
check_circle

H100 PCIe

80.0GB VRAM

Perfect
View All Compatible GPUs

Model Details

Family Qwen
Category Large Language Models
Parameters 72.00B
Context Length 131072

Similar Models

Qwen 2.5 14B 14.00B Qwen 2.5 32B 32.00B Qwen 2.5 7B 7.00B