NelsaHost
search Login
smart_toy
Llama Large Language Models

Llama 3.1 405B (405.00B)

Parameters
405.00B
VRAM (FP16)
810.0GB
VRAM (INT4)
202.5GB
Context
128000
check_circle View Compatible GPUs open_in_new View on HuggingFace

tune Quantization Options

Quantization VRAM Required Min GPU
FP16 (Half Precision) 810.0GB A100 / H100
INT8 (8-bit Integer) 405.0GB A100 / H100
Q4_K_M (GGUF 4-bit) 202.5GB A100 / H100
q3_k_m 162.0GB A100 / H100

Model Details

Family Llama
Category Large Language Models
Parameters 405.00B
Context Length 128000

Similar Models

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