Skip to main content

What Local AI can do?

First of all, we need to understand the overalll of all tools, models, and services:

Programming:

  • Claude is the king -> Critical  Planner (Expensive )
  • Codex is Queen -> Broad Planner ( Expensive )
  • GLM / Kimi K3 -> Worker 
  • Qwen, Gemma -> Free

Image Generation:

  • Google Gemini
  • GPT

Video Generation:

  • Seedance
  • Veo

CLI with good system prompts:

  • Claude
  • Pi 
  • Gemini 

Top Agentic Apps:

  • Hermes Agent

Local LLM

  • Fable gemma 
  • Fable qwen

What can local llm can do right now:

    does it smart enough to follow exactly the instruction of my language? does it able to do long tasks? how fast token generation it can do on our a 24 GB VRAM GPU 3090?