Modelsintro.com

Do you need to run the model on your own computer (privacy/offline)? │ ├─ YES → Can your GPU fit >16GB VRAM? │ │ │ ├─ YES → Use Llama 3.1 70B (or Mixtral 8x22B) │ └─ NO → Use Llama 3.1 8B, Phi-3-mini, or Gemma 2 9B │ └─ NO → Use a cloud API. What's your budget per million tokens? │ ├─ <$0.30 → Gemini 1.5 Flash, Claude Haiku, GPT-4o-mini ├─ $2-5 → GPT-4o, Claude 3.5 Sonnet (best for reasoning) └─ $10+ → GPT-4 Turbo, Claude Opus (only for legal/medical)

– your starting point for understanding the explosion of AI models. With hundreds of models being released every month (LLaMA, Mistral, GPT, Claude, Gemini, Stable Diffusion...), it's easy to feel lost. modelsintro.com

Use the search bar above, or browse by category: Do you need to run the model on