host ALL your AI locally

40 thoughts on “host ALL your AI locally”

• 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🖥🖥
  —————————————————
  ➡Lian Li Case: https://geni.us/B9dtwB7
  ➡Motherboard – ASUS X670E-CREATOR PROART WIFI: https://geni.us/SLonv
  ➡CPU – AMD Ryzen 9 7950X3D Raphael AM5 4.2GHz 16-Core: https://geni.us/UZOZ5
  ➡Power Supply – Corsair AX1600i 1600 Watt 80 Plus Titanium: https://geni.us/O1toG
  ➡CPU AIO – Lian Li Galahad II LCD-SL Infinity 360mm Water Cooling Kit: https://geni.us/uBgF
  ➡Storage – Samsung 990 PRO 2TB Samsung: https://geni.us/hQ5c
  ➡RAM – G.Skill Trident Z5 Neo RGB 64GB (2 x 32GB): https://geni.us/D2sUN
  ➡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

• My wife invested $30 into one of those Google Nest devices years ago. The lady residing inside still doesn't know the color of her underwear… so… what they pass off as AI these days doesn't impress me much. I remember back in my University days, I dabbled a bit modified the BASIC code for Dr. Eliza and re-branded my Pascal version Genesis. It wasn't much better, but it did manage to trick my friends into thinking they were talking to a real human. I even added a keystroke delay (about 20 words per minute) and it would apologize for being slow at typing. My version kept track of names, places, and didn't ask dumb questions.

  As for your video, good job, you always get that giddy watching your lawn grow? I am using Xubuntu 22.04 and I failed to get the same results as you. It took longer for it to pull those files and when I asked a question about song lyrics and it took a while just thinking about it. Then they read out very slow. I know my PC is aged but I do have a good Nvidia card. I guess if you are into AI design (aka neural network databases) you could have some fun with Ollama. Not exactly my thing when I can ask the pink Google Nest on the wall all the silly questions. I noticed you didn't tell people how to uninstall this service. I am sure they can look that up, if they are unaware of how to remove services in Linux. Thanks for the info.

• Sup, Chuck, can pls teach as more about Python and hacking

• Pop!_OS is my personal favorite and one ive been using for around 3 and a half years. Regular updates and all the features you could ask for out of the box. Found them when i bought my System76 laptop

• How do you combine gpus memory?

• Great walk through, I have been using ollama for a while, love the fact that you have shown how to install stable diffusion,I never expect that all this is possible in my lifetime 75 and still learning , I can't justify building a TERRY , a jetson orin will have to make do,

• I'm in process of building my own but instead I am running it through the offensive security training and some of my black hat tutorials. My problem is the audio interface, I really want to get it to talk back and take voice input.

• Me watching this on a generic tetris handheld @0:30

• Probably already been pointed out… AutomaticElevenEleven is easier to say.

• THIS IS GOLD

• Realistically this is a garbage setup for running AI models as you don't have enough vram. without nvlink (which is not supported on consumer gpus), your at 24GB of Vram..

• Great stuff! I've been messing with local AI projects for a few months using Pinokio, LM studio, and A1111 and I learned a few new things here. I tried a few AI Agent tutorials using CrewAI but didn't get too far. Can you do a walkthrough of getting started with CrewAI?

• Has anyone tried any of the uncensored LLM's?

• Now how can I incorporate it into a python program?

• you rock!

• 🔔A video on cloudflare Workers

• This kind of setup not only enhances privacy but also empowers users with direct control over AI interactions.

• Can this run in a rpi cluster and take advantage of the combined processing power?

• Great video Chuck

• Yeah, ill just go and pick up two 4090s… Oh.. hold up..

• Is there a way to hook a model up to vscode to replace github copilot?

• Thanks NC, how does concurrent users work?

• 2 4090s 💀

• Chuck, any chance of you adopting me???

• Thx great work with the show and please keep the content going you are really the best. A side project how you use obsidian would be nice, how it is setup and how you integrate it in your workflow thx a million 🙂

• Is there any way to link to excel so that you don’t have to buy tokens?

• Hey Chuck/Anyone ever. So I managed to follow along with you up until the part where you modify the settings to connect Stable Diffusion to Open WebUI. My Settings tab, does not have an option or tab for image settings at all? Weird..

• instead of saying automatic 1 1 1 1 you can say 11 11 "eleven eleven"

• Seriously after 6 months of watching only AI tutorial videos, this is the first time google recommended this epic beard wearing an AI wizard behind it. I have so much work ahead of me and clearly not enough beard in front of me.

• chuck can you make a direct link for a document…. I understand that membership is valuable but…. all I need is checklist with commands

• I wish I had a spare 2K for a server, a house, hell, even a vacation 😅.

• Can you get it to talk to it rather than type all the questions?

• I have this running in my lab!

• I'm not building a PC Qualcomm need to release those new chips quick.

• Very intresting video, can you please share the instructions you've given to Deborah ?

• As always, a great analysis. Newcomers often wonder if it's too late to navigate the financial market, but the market is always unpredictable. Trading has more advantages than simply holding, so it's important to learn before diving in. Active trades are necessary to ride the market's waves. Thanks to Linda Sue Baier insights, daily trade signals, and my dedication to learning, I've been increasing my daily earnings. Keep it up!

• How about ollama 3

• this is amazing, thanks Chuck. I have a question I am already using Comfyui and Automatic 1111, once implemented it will be run under llama prompt page, and hope it will be still reachable under regular comfyui interface, i am a bit afraid if some descripencies happen, when a new future or model and so on releases, it might not work after sometime and since verylittle people using SD by this way, due to a lack of tutorials, I might fail to fix it, what do you think?

• Is it also working well in other languages?

• Has anyone already tried bionic-gpt? It seems promising but I'm missing the time to test for now. @networkchuck, please test! 🙂

Comments are closed.