Transcript
Use with ChatGPT / Claude Auto-scroll A
The speaker introduces Jarvis running fully locally on a Mac and explains the goal of the video. He outlines the main sections: a live demo, hardware recommendations, model choices, and the free prompt pack.
Jarvis, what machine are you currently running on?
Your local Mac, sir.A rather powerful one, if I may say so.Powerful enough that I've stopped returning the cloud's calls.And before you ask, everything is local.Local brain, a local LLM, local voice, local memory.Nothing you say leaves this room, and nobody is listening in.The only thing I share with the internet these days is a healthy distrust.
Jarvis, switch to Gemma 4 12 billion parameters.
Gemma 4 fitted, sir.12 billion parameters, all of them local.Give me a moment, the fan and I are getting acquainted.
So, my personal AI assistant Jarvis now runs completely on a separate computer fully offline.So, in this video, I'm going to show you how Jarvis works, how you can build your own AI assistant like Jarvis, and run it fully offline on a machine like a Mac mini, a Mac Studio, or a Windowsmachine.We're talking local AI models, local voice, and local memory.No subscription and no API bills at all.And I'm also going to give you this full prompt pack and guide completely for free, which gives you all of the prompts and all of the guides you need to build your own Jarvis today.And then most importantly, I'm going to talk about which hardware works best, what to buy, how much unified memory you're actually going to need to run these models, which AI models run best on which machine, and how to
set all of it up.All right, let's get started.All right, so just so you guys know what's going to happen in the video, feel free to skip around if you want to.I'm going to have the chapters below.So, first of all, I'm going to start with a demo, so that way you can see exactly how Jarvis performs when it's running locally on my machine with all local models and everything completely private, right?And then afterwards, I'm going to talk about uh the difference between what type of machines, essentially what hardware is going to be required for running different AI models, and then I'm going to talk about which models will fiton the hardware of your choosing, depending on your budget.Like I said, there's going to be lots of differences here.And then of course, like I mentioned, I'm going to give you guys this uh full prompt pack, which is going to include all of the guides, including the hardware setup and everything else, and all of the prompts you
need to set up your own Jarvis on your own machine.And then I'm also going to quickly point out how you can uh install locally AI models using Ollama and then also an open source model for the voice cloning and voice interaction as well.Okay, so that's going to be the whole video here.So let's go ahead and start with a full demo first.
A full demonstration shows Jarvis switching between local and cloud brains, as well as changing voice modes. The speaker also shows how Jarvis accesses tools and personal files while staying private.
Now, for those of you have seen my previous video, this is Jarvis and what you're seeing spinning here, these are all of my local files, my local local brain, local second brain, right?And then Jarvis on the right hand side as you can see has multiple options as far as the look and feel of it and then it has access to a bunch of different tools.So he becomes a truly personal AI assistant.Now by default, I've been running him on Opus 5.5 and then on 11 labs, but now if I want to run him on my local machine, I can just basically interact with them and just say something like Jarvis,switch to your local brain.So now Jarvis is thinking.
Quen 3.5 fitted, sir.9 billion parameters running right here on your Mac.I'm smaller now, so do speak slowly.
So there you go.As you can see, Jarvis is now running.When I say local machine, by default I've set that cuz I like really like Quen 3.5, the 9 billion parameter model.Uh so it automatically switches to that, but I have a bunch of other local models because I have a pretty powerful machine, so I have a ton of different models that I've downloaded.So something like a Gemma 4, 12 billion parameters and higher models.So I'm going to talk about the hardware setup in a little bit.But again, same thing, it's very simple.All I have to say is just tell him to Jarvis, go ahead and switch to a Gemma 4, 12 billion parameters.That's all I have to tell him and then he understands and first of all finds out if he has access to that particular model and then of course he'll be able to switch his brain
Right then, sir.Consider me an upgrade less prone to existential crises than the previous model and marginally more patient with your requests.
Actually, you must have not heard me right, but you can see I had him also switch to the Gemma 3, 27 billion parameter model as well.So I have a bunch of different Gemma models that I've downloaded.But you get the idea, right?Like I'm I'm very I can very easily tell him to switch his models, his brain to different models.And I can always tell him to go back to the cloud brain as well.Jarvis, go back to your cloud brain.
Opus 55 online, sir.Full strength, full price, full sentences.
There you go.So now that's how easy it is for me to switch back and forth between the cloud brain, which operates with APIs, of course.I use Anthropic APIs.So he can switch very easily.And the same thing, right now he's running on 11 Labs for voice interaction.That's why you see how fast it is, but I can also switch his voice to run on a local voice clone using Voice Studio, which is an open-source platform that I'm going to talk about in a little bit.But same thing, I can say, "Jarvis, switch to your local voice."
There you go.So now Voice Studio opens up because I Voice Studio was turned off, so that's why it automatically opens that up.But if it's already if you have already Voice Studio open, then
How do I sound, sir?This is my local voice.
There you go.So that's how easy it is for us to So by the way, I I was going to point out that if you already have Voice Studio open, so we'll just quickly switch to that.But just because I had turned off the application, that's why it took a couple of seconds to open the application and then it said, "Now it's my local voice."Right?So that's how simple it is for me to have Jarvis move from cloud to local version completely.And like I said, now right now because I can have him run everything locally on my Mac, then it means that it's completely private and it has no access to anything outside.And of course, he can do a lot of things, right?So I have the ability for him to use all of the tool at his dis- all of his tools at his disposal, like the Gmails, Google Calendars of the world, Notion.
And then I can always give him more tools.And of course, he can always I can always have him interact with my local my second brain here and pull up any of the files or anything that I want.And it's very simple to do.So I can say something like, "Jarvis, pull up my free school community."So there you There you it's going to find out all of the folders
I've pulled up all the information, so you can read it yourself.Or if you'd like, say read it out loud and I shall.
There you go.So, now you can see it's pulling up all of the stuff that's related to my Free School Community.Of course, Free School Community is my business that I run where I provide you guys all of the free resources.And I also have a paid community.It's all part of my brand, right?So, that's how you can how I can interact with Jarvis to my second brain.Of course, I used Opus 5.I just realized I used Opus Opus 5.5, but this is very easily done with Quinn or other models as well.So, that was a quick demo.
The speaker compares Mac Mini and Mac Studio setups and explains why unified memory matters most for local AI. He gives practical guidance on which model sizes fit different machines and how performance changes with hardware.
I've done a bunch of different you know, I've done a lot of demos on how Jarvis works.You guys can check out my previous videos in my channel to see I mean, right now he has a ton of different features, right?I can interact with them just by my hands and stuff using hollow hands here.I can he can make phone calls on my behalf.I can call I can call him directly as well.I can interact with them via text, via Telegram, and so much more.So, like I said, if you're interested in checking out all of the functionalities of Jarvis, check out my previous videos there.All right.So, that was kind of a quick demo.Now, let's go ahead and jump in and talk about the different machines or the different hardware that you can set up and what type of models you run in.
So, what I'm going to do is focus on Mac Mini or Mac Studio and then on the Prompt Pack, I also have guide on oops.I have a guide on Windows machine using Nvidia card or Ryzen or if you have for instance, the Nvidia Spark, right?That's a powerful machine there.So, there's lots of information there for you guys to check out.But, in this particular example, I'm just going to quickly talk about the Mac Mini and Mac Studio because these are a good representation of what kind of the smaller version of a machine a local machine that people havelike a Mac Mini or a MacBook Pro like it's kind of have the same type of configuration.And then a Mac Studio which is a very very powerful machine, right?So, I'm going to compare these two and talk about the unified memory and which models run best on what type of hardware, and then you can make a decision on which route you want to go to.
All right, so the Mac Mini and Mac Studio, all of these specs are pulled directly from apple.com, so you guys can check out their website.But essentially, what I want to focus on the two most important things is uh the local storage and then most importantly, the unified memory, right?This is going to be the main thing here that we're going to focus on because that's what determines what kind of a AI model you can run locally on the machine, the latency, and how fast that interaction occursbetween you and your personal AI assistant.As you saw uh in my demo that you saw earlier, the latency is very low because I have a very powerful Mac.So, therefore, yours might be different depending on what you're running.So, if you have like a Mac Mini, the latency might be a little uh a little longer, so it's not going to be as natural, but it's still going to be pretty good enough.
But if you have like Apple 5 or Apple M5 Ultra like a Studio with the Apple M5 Ultra chip, then the interaction is going to be exactly or similar to mine there as well.All right, so the Apple Mini, the M6 chip right here, right now by default, it has 32 GB of unified memory, and then the uh Mac Studio, it could go up to 256 GB of unified memory, which isabsolutely insane.If you get this particular uh Mac Studio, you can essentially run any uh model, any open-source model, right?As I mentioned right here, unified memory is the whole game.And specifically on Mac, right?The good thing about the Mac Studio and the Mac software itself is the Mac machine itself is that uh the CPU and the GPU and the neural engine, they all share the same memory, which means that an AI
model that you download and run, it has to fit in that pool to run it run all of it, right?because the bigger the pool is, obviously, the bigger the brain will be for your AI assistant like Jarvis.So, for instance, for a Mac Mini, that the fact that it has 32 GB of unified memory
uh compared to like a Mac Studio, which is eight times more, you can get up to 256 GB of memory.You can think of the rule of thumb as for a model uh about points so 0.6 GB per billion parameters.You can think of it that way, right?So, if you have a 27 billion parameter model, then what you do is you just basically multiply that by 0.6, and that's the machine you end up with.So, let me explain a little further here.So, here are the models open-source models that uh run really well on Mac Mini and then also on Mac Studio.So, for the Mac Mini, if you have the 32 GB of unified memory, you can run something like Qwen 3.8 27 billion parameters pretty comfortably, right?Uh models like Gemma 4, the 26 billion parameters, uh the GPT-OSS 20 billion parameters, or these 12 billion 9 billion parameters, these are very comfortably run on a Mac Mini or a MacBook Pro.
But, if you want to run a bigger model, right?So, something like a Qwen 3.8 Flash, which is 125 billion which is a 125 billion parameter model, then you need something like a Mac Studio that has a unified memory of 256 GB or, like I said, if youwant to run something like a 70 billion parameter model, uh you can get a Mac Studio with 128 GB.And of course, the higher the unified memory, the more the cost is going to be.And this is something that you guys can compare on your own Mac uh on on apple.com, depending on where you are.Let's say if you're in the US or Canada or Europe, the prices are going to change.So, you can go ahead on apple.com, go to Mac Studio, and then pick the exact unified memory that you want, and then based on that, you will see the uh the price change there.
But, essentially, like I said, if you get the 256 GB unified memory, you can run majority of the models.And the great thing is you can always combine, so you can get two Mac Studios if you want to run like a three uh 1 trillion parameter model, right?And then as far as the um the uh storage itself, the storage you don't have to have that much storage.I mean, the Mac Studio automatically comes with a 1 TB of storage.And the good thing about storage is you can always get an external hard drive, right?So, that's not that big of a deal big deal.The biggest deal is or the biggest um factor for uh local machine or running locally uh these AI models is your unified memory.So, that's going to be the main focus if you want to run a bigger uh model there.
So, like I said, all of these details I just wanted to go over it so that way you guys can see uh which model fits your need.But like I said, all of this information and details I've explained here uh and exactly which model is going to run um really well on uh which particular machine there.
This section explains how to access the free and paid resources, including the prompt pack and ready-made Jarvis setup. The speaker then walks through downloading local models with Ollama and installing the open-source voice cloning tool.
Okay?So, like I said, you guys can check this out.And by the way, to gain access to this, uh so this is there's going to be two links in the description in the comments the first comment.The first one is going to be to the AI Workshop community.The second one is going to be to this free community.It's called AI Workshop Light, right?So, AI Workshop Light.Just go ahead and click on the second one.It's a completely free community.Uh once you click on join, you're going to you're going to come to the community right here.You're going to go to the classroom section.You're going to click on YouTube resources.And you'll have you'll have access to that uh prompt pack right there.They'll give you all of the guides including the prompts on how to build your own Jarvis cuz I have included the prompts right here.
Where did it go?There you go.So, the Galaxy the brain and a bunch of other ones so that way you can uh build your own type of Jarvis.But of course, if you want to have the finished Jarvis like mine here that you see everything is already set up and pretty.I mean, this took me like 3 months to build.That's going to be inside the paid community.That's going to be the first link.So, click on that.It's called AI Workshop.This is a paid community.Once you come here, all you have to do is go to the classroom section.And then we're right now on version uh 8.version 8.1.So, all you have to do is just download the zip files for your machine and you can run it up you can run it in like 5 minutes or so.The setup is pretty simple.
But like I said, if you want if you don't want to pay or join the paid community, uh you can uh essentially create this from scratch using that prompt pack guide.Now, as far as the models, how to download the models, all you have to do is just go to Ollama.So, just go ahead and create a free account and you click on get started, go to models and here you can search what a model.So, for instance, a Quin, right?You can search the entire Quin family of models.So, you can see Quin 3.5 gives you all of the the multiple billion parameter models that you can access to so that anywhere from 0.8 billion parameters, which is a very small model, all the way to 122 billionparameter model, right?So, this is something that's going to need to be the Mac Studio uh world or if you're using like Nvidia um a spark or something like that or a powerful Windows machine uh with lots of graphic cards.
So, that's where you can uh download these bigger models.But to download it is very very simple.Whatever model you choose, right?Scroll down to the bottom right here.So, let's say you want to choose this um 9 billion parameter model.So, all you have to do is click on that and then on your terminal just copy this command right here, right?So, uh oh to run that and to install it all you do is just Ollama pull and the name of the model.Again, all of this is inside the prompt pack I've given you guys.So, if you just go right here, yeah, so in case you don't remember, there all you have to do is just do Ollama pull Quin 3.5 9 billion parameter and then you do Ollama run.If you want to like run it to test it, right?Same thing the um the command is the same exact way.
So, you can do Ollama pull and then the name of the model.So, since this is Quin 3.5 9 billion, so let's say you want to download like the 27 billion one, right?So, if I go to the bottom here, oops, let me go back here.You click on the 27 and you just copy this and keep everything else the same.So, very very simple there.So, that's how you run the That's how you download the local models.And then as far as the cloning, so this is a voice studio, right?This is an open-source software that you can actually clone a voice, design your own voice, transcribe, like a really good software that's completely open-source.So, all you have to do is just search voice studio.There you go.And you just click on this one, free open-source voice cloning and dubbing.And this is exactly how you can grab And by the way, just if you want to just go to the GitHub, it's probably simpler.
So, you just go to GitHub, click on this one.And if you scroll down to the bottom,all you have to do is just copy Where did it go?Where is the installation here?Oh, here.You choose your machine.So, if you just click on this, it will show you exactly what to do to install.Again, same thing.I've added this on this prompt back as well for you guys to just be able to just copy and paste this here.Okay, so that's how you can download the models and then also the voice cloning there.
The speaker summarizes the basic workflow for building a local Jarvis: get the machine, install models, and add voice software. He closes by highlighting the community support, success stories, and final call to action.
And essentially, that's pretty much it.You don't need anything else after that, right?You download the models that you need.Of course, the first thing is buying the machine or whatever machine you have.And then afterwards, you download the local models and then download the voice cloning software and then pretty much it, right?The rest, if you want to build your own, like I said, follow the free prompt back here.Use these prompts to build your own Jarvis or like I said, if you want to be lazy, just go ahead and join the paid community so that way you can pick up Jarvis with this zip file right here.And of course, if you run into any issues, we have a ton of people in this amazing community of ours.You can post your questions.We can answer right away.And by the way, like a lot of my community members are now building their own versions of Jarvis.
Somebody just landed their first client selling Jarvis to somebody.So, lots of great things happening there if you want to check that out.Anyways, well, hopefully you find you guys found that helpful.Let me know if you have any questions in the comments below.Make sure you like, subscribe.Thanks for watching and I'll see you on the next one.