Home-labbing 7 GPUs for OCR lost to Google API on cost, researcher finds
RexDouglass · x · 2026-09-19
Researcher Rex Douglass shares his home-lab experiment: processing tens of millions of paper documents with 7 home GPUs, the cooling and electricity costs were never worth it versus just paying for the Google API. His interlocutor adds that no open-weight setup proved feasible at 20M-case scale. Conclusion: at scale, self-hosting almost always loses to cloud APIs.
Related event: Home 7-GPU Setup for OCR Proves Costlier Than Just Calling Google API(2 posts)→
More from Infra
- CoreAI Zoo hits App Store: run Qwen, Gemma and more fully on-device on iPhone — pcuenq · 2026-09-19
- MiniMax H3 ecosystem roundup: quantization, multi-GPU inference, LoRA tooling and workflows in one week — Just_Lingonberry_352 · 2026-09-19
- SpaceX to make gas-turbine blades in-house as AI power crunch strains supply chain — AccBalanced · 2026-09-19
- Running the 27B Bansai local model on just 5GB of RAM — hands-on test begins — draginol · 2026-09-19
- Inco Splash hits 144 tok/s running Qwen3.8-27B on an M5 Max, 3x faster than Ollama — TheMoonMidas · 2026-09-19
- Looped transformers study: 7.4B growth model matches GPT-3 13B with 20x less compute — burny_tech · 2026-09-19