Llama
Llama 3.1 405B
Total params
405B
Active params
405B
Layers
126
Hidden size
16384
Attention heads
128
KV heads (GQA)
8
Vocab size
128,256
Native context window
131,072
Native precision
BF16
Size this model
Opens the sizing calculator pre-filled with this model at BF16 weights / FP16 KV cache and a typical workload — sign in to run it and see GPU/cloud recommendations.
Size this model →