proxmox
host ALL your AI locally
host ALL your AI locally
#host #locally
“NetworkChuck”
Ready to get a job in IT? Start studying RIGHT NOW with ITPro: (30% off FOREVER) *affiliate link
Discover how to set up your own powerful, private AI server with NetworkChuck. This step-by-step tutorial covers installing Ollama, deploying a feature-rich…
source
To see the full content, share this page by clicking one of the buttons below |
Ready to get a job in IT? Start studying RIGHT NOW with ITPro: https://go.acilearning.com/networkchuck (30% off FOREVER) *affiliate link
Discover how to set up your own powerful, private AI server with NetworkChuck. This step-by-step tutorial covers installing Ollama, deploying a feature-rich web UI, and integrating stable diffusion for image generation. Learn to customize AI models, manage user access, and even add AI capabilities to your note-taking app. Whether you're a tech enthusiast or looking to enhance your workflow, this video provides the knowledge to harness the power of AI on your local machine. Join NetworkChuck on this exciting journey into the world of private AI servers.
📓📓Guide and Commands: https://ntck.co/ep_401
⌨⌨My new keyboard: Keychron Q6 Max: https://geni.us/0SGY
🖥🖥My Computer Build🖥🖥
—————————————————
âž¡Lian Li Case: https://geni.us/B9dtwB7
âž¡Motherboard – ASUS X670E-CREATOR PROART WIFI: https://geni.us/SLonv
âž¡CPU – AMD Ryzen 9 7950X3D Raphael AM5 4.2GHz 16-Core: https://geni.us/UZOZ5
âž¡Power Supply – Corsair AX1600i 1600 Watt 80 Plus Titanium: https://geni.us/O1toG
âž¡CPU AIO – Lian Li Galahad II LCD-SL Infinity 360mm Water Cooling Kit: https://geni.us/uBgF
âž¡Storage – Samsung 990 PRO 2TB Samsung: https://geni.us/hQ5c
âž¡RAM – G.Skill Trident Z5 Neo RGB 64GB (2 x 32GB): https://geni.us/D2sUN
âž¡GPU – MSI GeForce RTX 4090 SUPRIM LIQUID X 24G Hybrid Cooling 24GB: https://geni.us/G5BZ
🔥🔥Join the NetworkChuck Academy!: https://ntck.co/NCAcademy
**Sponsored by ITProTv from ACI Learning
Oh the hardware envy
You can put in all the guardrails when ChatGPT will write the paper for them.
But hey. That is good. The future is shaping! I don't think that the future kids can only be smart by memorizink tons of books in their mind.
A definition of a smart person who can solve issues with all the available tools. Back before the internet this was the library. Did you have to learn it? – Probably yes. Do you have to learn it today? Probably no because you are no more than 5 feet from a smart device with all the wisdom of all the books ever written.
Awesome tutoril though. Subscribed and watching! Thanks Chuck!
Private AI does not exist you guys, there is nothing private about this, except the calculations are handled on the client computer, the information is still send to the big bad cloud and also being pulled from the cloud. Does you really think a 5 GB file can fit all the information from the internet? The IMDB database alone is much bigger than that. Pull the network plug or wifi and the software becomes completely stupid and unusable. There is your so called AI, it's all fake! AI is not intelligent and can't really learn, you can add new information to it yes, but that does not mean it actually understands and learns. It's all just code trying to desperately make it seem like it's a human but it's not. And if you knew how all these AI companies have ten thousands of people working on the backend adjusting all the answers your opinion on AI would forever change, so much for "learning" haha. Does that mean it doesn't have any usecase? No it's good at comparing/analysing big chunks of information and it does faster than the human brain. However you have to set all the rules.
Thank you for the video; I have a question for you: If I install GPU cards in my computer and run Ollama locally, will I receive a high electricity bill?
running docker with sudo is such a newbie thing
But how do you run it in a container?
I was check academy and You have mess in formating in sudo command in this lesson, can you fix this? or report issue? 😛
I'm new to this channel. This is pretty cool stuff! Question: What software/hardware is being used to draw directly on-screen like that? I love it!
with using ollama web ui, passing prompt to automatic 1111, how can I passing the nagative prompts? and other settings such as CFG scale, sampling method etcs? or is it limited
What about LMStudio
Did the whole job with no coffee break? Unbelivable 🙂
Llama 3 is much better.
Basically, ChatGPT is nothing more than a glorified Alexa. You can query it, and it will respond with an answer…
…but there is literally no spark of intelligence going on. No planning, no independent thought, no consciousness, no brainstorming, no designing, no continuous dialog going on inside like a human… just a blank slate. You might as well be typing a query string into Wikipedia.
hello, wonderful video. could you do me a favor and run Llama3 70b so I can see how well it runs? thank you
2x 4090 liquid cooled, dude, you're overkilling this, haha
how were you able to get the msi liquid x to 480w? My 2 are stuck at 450w even if i flip toggle switch to Silent or Performance.
Great video! On todays refurbished market you can find older AI/deeplearning GPU's like tesla K80 and so on. Would that be a good investment for an AI homeserver?
great
Cool & all, but 99.9% of PC owners don't have 2x4090s casually lying around. Most probably don't even have a single 4090, so for whom is this video for, exactly? If you want to actually teach people to use generative models locally, start with something that most people can run. 7B models can fit on 8GB GPUs and will run fast even on slower hardware. Front-ends like SillyTavern offer a whole list of compatible APIs, online AND offline, so that the user can configure everything to his needs/possibilities. Why not teach that?
But why didn't Ubuntu work?
This is amazing, also looking into running a local autogpt bot. do you have any suggestions?
So it seems like an amazing system as well as a amazing electricity bill.What do you pay a hundred dollars a month just to run it
Off-topic question what happens to you?When you don't drink coffee, do you go through Massive crazy withdrawals and bad mood swings
no .. my computer won't work, and it sucks that I can't train AI on the cloud because I can't afford it nor can I train it locallyy because I can't afford it [if anyone has a quick solution for at least 6 months, it should be more than enough to get my first buck which will undoubtedly set me up for the best equipments] nice video BTW 🙃
Doesn't work for me on two different computers so I'll have to download the windows installer instead.
EDIT: I managed to get it working. For anyone else who might experience problems, make sure to disable your anti virus software which is what I forgot to do.
lmao the two 4090 🫣
Good video
Good video
PUT ARCH ON TERRY CMON BRO I got a 3950X with dual 4070s running Arch and Gentoo nice keyboard btw I have a V4
Can you connect to that private AI from a cellphone to be used as a personal assistant instead of Bixby for example?
Fire
use llama3
Bro I fucking love pop os… use it on my home lab machine. Gives me macOS vibes but without all the restrictions