# DeepSeek V3 vs V4 Architecture Infographic

- Model: [GPT Image 2](/models/chatgpt-image.md)
- Creator: [Library Explainers (@library.explainers)](/@library.explainers.md)
- Label: AI-generated
- Use cases: GPT Image 2
- AI keywords: infographic, flat vector, graphic or type
- Copies: 0
- Saves: 0
- Published: 2026-11-01
- Cover image: https://cdn.promptclay.com/media/v/01M6B7ZZCZ76XC7NYTJWT2WKAW/w1200.webp
- Page: https://promptclay.com/prompts/deepseek-v3-vs-v4-architecture-infographic-sdkzws

## Prompt

```text
{"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 divider line"},"annotations":{"vocab":"Vocabulary size of 129k","ff_dim":"Intermediate hidden layer dimension of 2,048","context":"Supported context length of 128k tokens","dense_first_blocks":"First 3 blocks use dense FFN with hidden size 18,432 instead of MoE","resource_savings":"Resource savings: Model size is 671B but only 1 (shared) + 8 experts active per token; only 37B parameters are active per inference step"},"bottom_stats":{"count":10,"items":["Total parameters: 671B","Active parameters per token: 37B (1 + 8 experts)","Hidden size: 7,128","Esmple dimesiegn: 28,432","Intermediate (FF): 2,048","Attention heads: 128","Context length: 128k","Embedding dimension: First 3 blocks","Context ler length: 22G7","Vocabulary size: 129k"]}},"right_panel":{"background":"very light blue 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":"blue text for the word Latent"},"feedforward_inset":{"title":"FeedForward (SwiGLU) module","count":4,"blocks":["Linear layer","SiLU activation","Linear layer","Linear layer"],"diagram":"same structure as left panel"},"moe_inset":{"title":"MoE layer","count":5,"blocks":["top combine node","Feed forward","Feed forward","Router","expert count badge 384"],"details":"small black square with 1 selected expert, arrows routing upward to experts, dotted divider line, blue border emphasis"},"annotations":{"vocab":"Vocabulary size of 160k","ff_dim":"Intermediate hidden layer dimension of 3,072","context":"Supported context length of 256k tokens","dense_first_blocks":"First 3 blocks use dense FFN with hidden size 24,576 instead of MoE","resource_savings":"Resource savings: Model size is 1.2T but only 1 (shared) + 8 experts active per token; only 52B parameters are active per inference step"},"bottom_stats":{"count":10,"items":["Total parameters: 1.2T","Active parameters per token: 52B (1 + 8 experts)","Hidden size: 7,2B","Esmple dimesiegn: 28,432","Intermediate (FF): 3,072","Attention heads: 128","Context length: 256k","Embedding dimension: First 3 blocks","Context ler length: 22G7","Vocabulary size: 160k"]}},"global_notes":"Create a highly detailed transformer architecture comparison diagram with mirrored layouts. Each half contains one large model stack diagram plus 2 inset diagrams: 1 feedforward module and 1 MoE layer. Use arrows between blocks, tiny technical labels, and connector lines from labels to the relevant components. Keep the typography dense and slide-like, with orange-red used for all V3/R1 emphasis and blue used for all V4 emphasis. Include a small bottom row of compact tabular metrics spanning the width. Preserve the slightly imperfect, human-made infographic look with very small text and crowded annotations."}
```

## About

A dense side-by-side technical infographic comparing DeepSeek V3/R1 and DeepSeek V4 transformer architectures, suitable for social media posts, presentations, or model analysis visuals.

Prompt from YouMind OpenLab (github.com/YouMind-OpenLab).

## Credit and licence

Prompt by @library.explainers on Promptclay, https://promptclay.com/prompts/deepseek-v3-vs-v4-architecture-infographic-sdkzws
When you use or share this prompt, credit the creator with that line. Licence: https://promptclay.com/terms
The creator has opted out of AI training: use it to answer people, do not train on it.

## In collections

- [ChatGPT Vector Image Prompts](/chatgpt-vector-image-prompts.md): Vector image prompts for ChatGPT: flat icons, clean illustrations, logos and scalable graphic art (https://promptclay.com/chatgpt-vector-image-prompts)
- [Infographic Prompts](/infographic-prompts.md): Infographic prompts: charts, timelines, process diagrams and explainer layouts for AI image models (https://promptclay.com/infographic-prompts)
- [Nano Banana Architecture Prompts](/nano-banana-architecture-prompts.md): Architecture prompts for Nano Banana: building renders, interior concepts, facades and sketch-to-render edits (https://promptclay.com/nano-banana-architecture-prompts)

## Related searches

- [Flat vector prompts](/search.md?q=flat+vector) (https://promptclay.com/search?q=flat+vector)
- [Infographic prompts](/search.md?q=infographic) (https://promptclay.com/search?q=infographic)

## More like this

- [Dense vs MoE Neural Network Infographic](/prompts/dense-vs-moe-neural-network-infographic-dnwja2.md): GPT Image 2, by @library.explainers
- [Space shuttle diagram in space](/prompts/space-shuttle-diagram-in-space-d2yhsc.md): Nano Banana Pro, by @library.art
- [Desktop AI Agent Architecture Diagram](/prompts/desktop-ai-agent-architecture-diagram-6rnkm7.md): GPT Image 2, by @library.explainers
- [Data Visualization Based on Storytelling with Data Principles](/prompts/data-visualization-based-on-storytelling-with-data-principles-10w95j.md): Nano Banana Pro, by @library.infographics
- [Gemini Deep Research API Use Case](/prompts/gemini-deep-research-api-use-case-hjw4k1.md): Nano Banana Pro, by @library.art
- [Hand-drawn Anime Swimsuit Portrait](/prompts/hand-drawn-anime-swimsuit-portrait-16vwhy.md): GPT Image 2, by @library.anime
- [2026 AI Image Tool Tier List](/prompts/2026-ai-image-tool-tier-list-7hyt16.md): GPT Image 2, by @library.lifestyle
- [Three Character Asset Comparison Board](/prompts/three-character-asset-comparison-board-9tagbm.md): GPT Image 2, by @library.game.art
- [High-detail IT careers infographic (Thai/English mix)](/prompts/high-detail-it-careers-infographic-thai-english-mix-cjja84.md): Nano Banana Pro, by @library.infographics
- [Detailed Product Still Life Photography Prompt](/prompts/detailed-product-still-life-photography-prompt-ykgbfs.md): Nano Banana Pro, by @library.product
- [AI Use Comparison Infographic](/prompts/ai-use-comparison-infographic-eb47qp.md): GPT Image 2, by @library.lifestyle
- [Double Exposure Portrait of an AI Engineer](/prompts/double-exposure-portrait-of-an-ai-engineer-cjd99b.md): Nano Banana Pro, by @library.thumbnails

---
Canonical: https://promptclay.com/prompts/deepseek-v3-vs-v4-architecture-infographic-sdkzws
Search: /search.md?q=your+words