Dragonfruit AI runs its entire inference on Macs, claims a 5x cost edge over rivals
akumar · x · 2026-10-19
The founder shares that AWS once accused them of being a fake AI company — millions spent on EC2, zero on inference or training. The reality: 100% of Dragonfruit AI's real-time video inference runs on Apple Mac hardware, with no AWS tax and no Nvidia tax.
- They run what they claim is the world's largest distributed cluster of Macs for real-time video AI — mostly Mac Minis racked in micro-colos and shipped to customers — across thousands of locations on every continent but one
- This yields roughly a 5x cost advantage: if a competitor's total annual cost (hardware + license) is $10,000, theirs is about $2,000
- The founder stresses it was economics, not a stunt, and the bet has held for four years
More from Infra
- ONNX to Transformers.js: running models directly in your browser — JosephJacks_ · 2026-10-23
- MiniMax M3.1 Flash free for 3 days on 0G, with 1M context and 512K output — MiniMax_AI · 2026-10-23
- "We bet on Cloudflare and it paid off": R2 and D1 at billion scale — dinasaur_404 · 2026-10-23
- Public data is drying up; private training data is turning into a browsable catalog — SucceededMind · 2026-10-23
- Tracking Chip Heat Propagation with a Thermal Master P3 Camera — yaroslavvb · 2026-10-23
- Bloom Energy Q3 revenue hits $1.24B, up 138% YoY, raises FY26 guidance to $4.4-4.6B — Beth_Kindig · 2026-10-23