Explore local ai

Running specialist Dots agents as provisioned employee-like machines inside OpenAI

"We have them running on Mac Mini. We provision them exactly like employees — we mint a new little identity and then it's got IAM and the roles. We give them a very premium machine as well because the model is incredibly capable under the hood."

Tibo Sottiaux

Running Codex and other AI agents 24/7, remotely controllable from phone or MacBook Pro while traveling

"The Mac Mini setups remain supreme. I just bought a Mac Mini. In fact, I just bought another Mac Mini. I want to have access to Codex wherever I go. I want one instance of Codex running 24/7 and I'm going to be setting that up."

Riley Brown

Running local open source AI models to avoid sharing sensitive IP with closed AI providers

"I literally just ordered two Mac Studio M5s. We're going to be running local models and we're moving off Claude for a lot of our sensitive data."

Chamath Palihapitiya

Desktop computing for local AI model processing

"Having that work on the incredible hardware I'm gonna have on my desktop on this $12,000 Mac Studio."

This Week in Startups

Base models for fine-tuning and post-training work

"What we did to initially gain some popularity was like Llama was putting out base models. We fine-tuned those into something that we thought would be like something the market would want."

Dylan Rolnick

"We have a whole bunch of Llama and Mistral running and stuff internally and a bunch of OpenAI."

Mike Cannon Brooks

Running AI models on-premises in 15 minutes via an Ethernet-connected appliance

"Aboc has changed their name, so I got to give them a proper shout out here. They're now go.ai. You plug it in and AI happens on-prem in 15 minutes. You own it. Look at that gunmetal steel. Looks like an Apple product. Go to go.ai."

This Week in Startups

Running AI models locally for privacy, cost control, latency, and understanding local vs. cloud architecture

"If you could run these models locally with something like Ollama, LM Studio, you start to understand what can happen on your own machine and what needs the cloud and what needs to touch private docs and what should stay behind the wall."

Greg Isenberg

Running local AI models with GUI interface

"LM Studio is the one I'd start non-technical people on because it has a real interface. It's got a model browser. You click and it runs."

Greg Isenberg

Running AI models locally for privacy, cost control, latency, and understanding local vs. cloud architecture

"If you could run these models locally with something like Ollama, LM Studio, you start to understand what can happen on your own machine and what needs the cloud and what needs to touch private docs and what should stay behind the wall."

Greg Isenberg

Running local AI models via command line

"There's two main names to know, Ollama and LM Studio. Ollama is usually the favorite of a lot of my developer friends because it runs from the command line."

Greg Isenberg