What needed a data center in 2020 now runs at home: 5 local AI open-source stacks
alex_verem · x · 2026-10-20
alexverem's series recap: five AI tasks that needed a data center in 2020 — chatbots, speech to text, photo face search, text-to-image, and robots that learn — now run at home.
- Chatbot: Ollama runs DeepSeek, Qwen, Kimi and OpenAI's open model locally, no account, nothing leaves your machine (183k stars)
- Speech to text: whisper.cpp transcribes hours of audio offline on a normal laptop (54k stars)
- Face search: Immich is self-hosted Google Photos finding faces, objects and places (116k stars)
- Text-to-image: ComfyUI generates images and video on your own GPU (140k stars)
- Robot learning: Hugging Face's LeRobot teaches robot arms by demonstration, from low-cost arms to humanoids
Core thesis: the threshold for AI capability has shifted from the data center to the home.
Related event: Five Data-Center AI Tasks From 2020 Now Run at Home in 2026(3 posts)→
More from Infra
- NVIDIA's $500B AI infra deal had "no obvious provenance" as PE debt talks stall — mjdramstead · 2026-10-20
- The Local Computing Rebellion: Subscription Fatigue and Forced AI Drive a Shift Back On-Premises — DavidLinthicum · 2026-10-20
- DeepSeek also open-sources deepseek-recipe, replicating official API token encoding logic — deepseek_ai · 2026-10-20
- DeepSeek open-sources DeepInfer, the production inference framework behind DeepSeek-V4.1-Flash — deepseek_ai · 2026-10-20
- Scott Hanselman serves local inference to his whole house from a Surface Laptop Ultra — lee_stott · 2026-10-20
- DeepSeek-V4.1-Flash quantized to 2-4 bit mixed precision for dual RTX PRO 6000 with 0.1306 KL divergence — TheZachMueller · 2026-10-20