rupayanism

newest first

all setups

Every setup on this site, with the numbers. Most of them are the write up behind a reel.

  1. Pick the right GGUF for your RAM (the quant picker)2026-09-16 · reel 54
  2. Nine agent skills trending this week, plus a SKILL.md starter2026-09-16
  3. Run Microsoft BitNet on your CPU2026-09-13 · reel 51
  4. Keep your AI assistant running when your laptop is closed2026-09-11 · reel 49
  5. ElevenLabs $100, your GPU 6 cents? The exact VoiceStudio setup2026-09-10 · reel 48
  6. Nine harnesses, one model, and a 17x spread in the bill2026-09-09 · reel 47
  7. Run a 125B model on a 48GB laptop (slotstream setup)2026-09-08 · reel 46
  8. Fine tune an 8B model on a 4GB laptop GPU (Soup setup)2026-09-07 · reel 45
  9. Train your own LLM for 43 cents and 2 hours (minimind setup)2026-09-06 · reel 44
  10. Send your AI pictures of your code instead of the code (pxpipe setup)2026-09-04 · reel 43 · updated 2026-09-19
  11. Give your coding agent a throwaway Linux VM (clawk setup)2026-09-02 · reel 23
  12. Rebuild Redis from an empty file (Ship That Code setup)2026-08-31 · reel 36
  13. 7.4 billion free AI tokens a month2026-08-30 · reel 34
  14. Run a 20B AI model in 7GB RAM2026-08-29 · reel 42
  15. Run a 35B model on a 300 euro computer (CarWatch setup)2026-08-28 · reel 41
  16. Run a 27B model in 6.2GB, no GPU (Qwen3.8 setup)2026-08-26 · reel 40
  17. Run a 744B model in 9.9GB of RAM (Colibri setup)2026-08-24 · reel 31
  18. Run a 30B model on a 2016 desktop (quantprobe setup)2026-08-20 · reel 39
  19. Run a 2.78 trillion parameter model in 8GB (Kimi K3 setup)2026-08-19 · reel 27
  20. Run an 80B model in 4.3GB of RAM (Swiftlet setup)2026-08-18 · reel 21
  21. Run AI on a laptop with no graphics card2026-08-13 · reel 20
  22. Run a 14MB AI on a Raspberry Pi (Needle2 setup)2026-08-12 · reel 15
  23. Run a 70B model on a 4GB card (AirLLM setup)2026-08-11 · reel 14
  24. The weird web list2026-08-11 · reel 18
  25. How I Built My JARVIS2026-08-08