NelsaHost
search Login
smart_toy
Llama Large Language Models

Llama 3.1 8B (8.00B)

Parameters
8.00B
VRAM (FP16)
16.0GB
VRAM (INT4)
4.0GB
Context
128000
check_circle View Compatible GPUs open_in_new View on HuggingFace

tune Quantization Options

Quantization VRAM Required Min GPU
FP16 (Half Precision) 16.0GB RTX 4080
INT8 (8-bit Integer) 8.0GB RTX 3070 / 4060
Q4_K_M (GGUF 4-bit) 4.0GB RTX 3070 / 4060
q3_k_m 3.2GB 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 4090

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 Llama
Category Large Language Models
Parameters 8.00B
Context Length 128000

Similar Models

Llama 3 70B 70.00B Llama 3 8B 8.00B Llama 3.1 405B 405.00B Llama 3.1 70B 70.00B