#107 Robin: Running Gemma & Ollama Locally, Private Workflows
Got something to say to this podcast? Send a voicemail, and you might hear yourself on the next episode!
Think you need a $10,000 GPU rig and a massive API budget to build elite AI workflows? Think again. The biggest sleeper opportunity in 2026 isn't another massive cloud API—it’s the hyper-optimized, open-source LLMs running completely offline on the laptop you already own.
Today, we are demystifying Local AI. We're tearing down the assumption that tools like Hugging Face, Ollama, and LM Studio are strictly for hardcore developers. If you have customer data that legally cannot touch a cloud…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.