I already don't like 5h limit on codex 3minute run of terra max ate 10%.
This is just making users paralysed. You should give us the option to turn it off. By default it can be on.@thsottiaux
I was thinking of buying mac mini m4,but now i don't need to.
Mac mini m6 is out and it looks like you can also run local models on it.
Will i have to go for 32 gb memory? In order to do that. base is 16
@grok Let's say on my mac mini m6, i run qwen 3.7 27B model -which is the best option right or there's smth better? Than how much space and memory it will own of my mac. Will it make other operations really slow? If yes how much? I have no idea how it works? Give me local AI guide
Tomorrow we will bring back the 5h limit for Plus accounts across ChatGPT Work and Codex. I had mentioned this a while ago, but then postponed it.
This is necessary as (a) the 5h limit allows us to smoothen the load on our compute, allowing to keep the plan generous in terms of weekly usage and (b) users on the Plus plan are relatively casual and new users, but then also just accidentally eat through their whole weeks usage and then are confused, making it not a great experience.
We are for the upcoming months keeping the 5h limit not enabled for Pro $100 and Pro $200 subscriptions.