Llama 4 Scout 17B-16E
Meta Llama 4 Scout 17B-16E. 48 decoder layers with interleaved local (RoPE chunked, ×40) and global (NoPE, ×8) attention, MoE FFN (16 experts, top-1). TP=8 on 8×B200 (4×B200×2): 40/8=5 q-heads, 8/8=1 kv-head.
Architecture Overview
Loading visualization...
Architecture Summary
22
Total Modules
10
Blocks
12
Kernels
11
Traced Kernels