🤖

Series · Part 13 of 21

Practice
AI Demystified
Abhishek Saha
Abhishek Saha · 🤖 AI / ML

Do You Really Need GPT-4?

Frontier models are impressive — and often the wrong choice. Here's the model selection map: cost, capability, latency, and when local wins.

#ai #llm #model-selection #efficiency #quantization #local-inference

The default is to reach for the biggest model. That’s usually wrong. Cost, latency, privacy, and task specificity all point toward smaller models more often than you’d think.

MODEL SELECTION GUIDE
Which Model Should You Use?
HOVER BUBBLES FOR DETAILS — BUBBLE SIZE = SPEED (larger = faster)
Cost per M tokens →Task generality ↑cheapmidexpensivenarrowgeneralbubble size = speedLocal (Ollama)Small API(Gemma, Phi)Mid-tier(Sonnet, 4o-mini)Frontier(GPT-4o, Opus)Fine-tunedSmall Model
Costs approximate as of 2025 — always verify current pricing with providers. Rules of thumb, not hard limits.

The right model depends on the task, not prestige. Most production AI runs on mid-tier or smaller — frontier handles only the tail that genuinely needs it.

Next up: You’ve picked your model. Part 14 covers the real cost: why tokens cost what they do, why inference is slow, and how to fix both.

AI Demystified · 16 of 21 published

  1. 0 Grounding 5 Mental Models You Need Before Diving Into AI
  2. 1 Foundation What Happens When You Ask AI Something?
  3. 2 Foundation Transformers — The Architecture That Changed Everything
  4. 3 Foundation How AI Learns, Thinks, and Decides
  5. 4 Foundation How AI Reads Your Words
  6. 5 Foundation Why AI Forgets
  7. 6 Foundation Why AI Lies (And Doesn't Know It)
  8. 7 Foundation What AI Cannot Do
  9. 8 Foundation How AI Reasons (And Why It Sometimes Breaks)
  10. 9 Practice Prompt Engineering — How to Talk to AI
  11. 10 Practice Embeddings & Vector Databases — The Memory Layer of AI
  12. 11 Practice RAG Explained — How AI Knows What You Didn't Train It On
  13. 12 Practice Fine-tuning vs. Prompting — When to Use Which
  14. 13 Practice Do You Really Need GPT-4?
  15. 14 Practice Latency, Tokens, and Cost — The Physics of AI Products
  16. 15 Practice How Do You Know AI Is Actually Working?
  17. 16 Hands-On Coding Setup — Your AI Development Environment soon
  18. 17 Hands-On MCP Tool Calling — How AI Uses Tools soon
  19. 18 Hands-On AI Agents — Beyond Chatbots soon
  20. 19 Hands-On Build Your First Real AI App soon
  21. 20 Hands-On Token Optimization — Spend Less, Get More soon
← Part 12 Fine-tuning vs. Prompting — When to Use Which Part 14 → Latency, Tokens, and Cost — The Physics of AI Products

Related posts

Enterprise Master Data Cleaning: The Business Case for SAP Supplier Data
AI / ML ·

Part 1 — Enterprise Master Data Cleaning

Enterprise Master Data Cleaning: The Business Case for SAP Supplier Data

Why dirty vendor master data quietly costs enterprises millions, how AI helps, and the operating model that makes it safe. Part 1 of the series, for business and leadership.

Read
master-data sap data-quality enterprise
Embeddings and Vector Search, Step by Step: Finding Duplicate Suppliers
AI / ML ·

Part 2 — Enterprise Master Data Cleaning

Embeddings and Vector Search, Step by Step: Finding Duplicate Suppliers

Learn embeddings, distance, vector databases, semantic search and a mini RAG one step at a time, by finding duplicate suppliers in a small dataset.

Read
master-data sap data-quality embeddings
newsletter

Get new posts in your inbox

No spam. No digest. Just a note when I publish something new.

Discussion