DeepSeek V3 vs V4 Architecture Infographic

Prompt

{"type":"side-by-side AI architecture comparison infographic","style":"clean technical diagram, white background, thin black outlines, rounded rectangles, dashed callout boxes, color-coded highlights, presentation-slide aesthetic, vector infographic","canvas":{"aspect_ratio":"2:1","resolution":"wide horizontal"},"title_row":{"left_title":"DeepSeek V3/R1 (671 billion)","right_title":"DeepSeek V4 (1.2 trillion)","left_title_color":"bright orange-red","right_title_color":"bright blue"},"layout":{"columns":2,"sections":[{"title":"DeepSeek V3/R1 (671 billion)","position":"left half","count":9,"labels":["Vocabulary size of 129k","FeedForward (SwiGLU) module","Intermediate hidden layer dimension of 2,048","MoE layer","Supported context length of 128k tokens","First 3 blocks use dense FFN with hidden size 18,432 instead of MoE","Sample input text","Embedding dimension of 7,168","128 heads"]},{"title":"DeepSeek V4 (1.2 trillion)","position":"right half","count":9,"labels":["Vocabulary size of 160k","FeedForward (SwiGLU) module","Intermediate hidden layer dimension of 3,072","MoE layer","Supported context length of 256k tokens","First 3 blocks use dense FFN with hidden size 24,576 instead of MoE","Sample input text","Embedding dimension of 8,192","128 heads"]},{"title":"bottom comparison table","position":"bottom full width","count":10,"labels":["Total parameters","Active parameters per token","Hidden size","Esmple dimesiegn","DeepSeek V3/R1","Intermediate (FF)","Attention heads","Context length","Embedding dimension","Vocabulary size"]}]},"left_panel":{"background":"very light gray rounded rectangle","main_stack":{"count":8,"blocks":["Tokenized text","Token embedding layer","RMSNorm 1","Multi-head Latent Attention","RMSNorm 2","MoE","Final RMSNorm","Linear output layer"]},"side_module":"RoPE attached to the attention block on the left side","attention_block":{"label":"Multi-head Latent Attention","accent":"orange-red text for the word Latent"},"feedforward_inset":{"title":"FeedForward (SwiGLU) module","count":4,"blocks":["Linear layer","SiLU activation","Linear layer","Linear layer"],"diagram":"two branches multiplied, then projected"},"moe_inset":{"title":"MoE layer","count":5,"blocks":["top combine node","Feed forward","Feed forward","Router","expert count badge 256"],"details":"small black square with 1 selected expert, arrows routing upward to experts, dotted ...