FREE Local LLMs on Apple Silicon

FREE Local LLMs on Apple Silicon | FAST!

Рет қаралды 130,613

29 күн бұрын

Step by step setup guide for a totally local LLM with a ChatGPT-like UI, backend and frontend, and a Docker option.
Temperature/fan on your Mac: www.tunabellysoftware.com/tgp... (affiliate link)
Run Windows on a Mac: prf.hn/click/camref:1100libNI (affiliate)
Use COUPON: ZISKIND10
🛒 Gear Links 🛒
* 🍏💥 New MacBook Air M1 Deal: amzn.to/3S59ID8
* 💻🔄 Renewed MacBook Air M1 Deal: amzn.to/45K1Gmk
* 🎧⚡ Great 40Gbps T4 enclosure: amzn.to/3JNwBGW
* 🛠️🚀 My nvme ssd: amzn.to/3YLEySo
* 📦🎮 My gear: www.amazon.com/shop/alexziskind
🎥 Related Videos 🎥
* 🌗 RAM torture test on Mac - • TRUTH about RAM vs SSD...
* 🛠️ Host the PERFECT Prompt - • Hosting the PERFECT Pr...
* 🛠️ Set up Conda on Mac - • python environment set...
* 🛠️ Set up Node on Mac - • Install Node and NVM o...
* 🤖 INSANE Machine Learning on Neural Engine - • INSANE Machine Learnin...
* 💰 This is what spending more on a MacBook Pro gets you - • Spend MORE on a MacBoo...
* 🛠️ Developer productivity Playlist - • Developer Productivity
🔗 AI for Coding Playlist: 📚 - • AI
Repo
github.com/open-webui/open-webui
Docs
docs.openwebui.com/
Docker Single Command
docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main
- - - - - - - - -
❤️ SUBSCRIBE TO MY KZfaq CHANNEL 📺
Click here to subscribe: / @azisk
- - - - - - - - -
Join this channel to get access to perks:
/ @azisk
- - - - - - - - -
📱 ALEX ON X: / digitalix
#machinelearning #llm #softwaredevelopment

Пікірлер: 267

@camsand6109 27 күн бұрын

This channel is the gift that keeps on giving.

@JosepCrespoSantacreu 27 күн бұрын

Another great video Alex, I really enjoy your videos. And I really appreciate your perfect diction in English, which makes it easy to follow your explanations even for those who do not have English as their first language.

@3monsterbeast 5 күн бұрын

This channel is going to be growing so fast; you make great videos that are very helpful!

@asnifuashifj91274 27 күн бұрын

Great video Alex! yes please make videos on image generation!

@cstenger 5 күн бұрын

I like the manual installation process because it uses less resources than having docker running all the time on your mac. thanks for the tutorial, I really enjoyed doing it and seeing how it works.

@aldousroy 27 күн бұрын

Awesome thing waiting for more videos on the way

@ReginaldoKono 19 күн бұрын

Yes Alex, you will help us more if we could learn with you how on how to add an image generator as well. We thank you for your time and colaboraron. Your channel is a must have subscription in it now-a-days.

@AC-cg6mf 25 күн бұрын

I really like that you showed the non-docker install first. I think too many rely on docker black-boxes. I prefer this. Thanks!

@philipo1541 21 күн бұрын

Dockers are not a black-box. You can get it in them, and change stuff!!!

@veccio 4 күн бұрын

Respectfully, Docker need not be a black box. Don’t be afraid to tinker and dig in. :) But I get how doing it manually forces you to touch different parts.

@7764803 27 күн бұрын

Thanks Alex for videos like this 👍 I would like to see Image generation follow up video 😍

@ChrisHaupt 27 күн бұрын

Very interesting, will definitely be trying this when I get a little downtime!

@gustavohalperin 24 күн бұрын

Great video!! And yes, please add a video explaining how to add the images generator.

@iv4sik 23 күн бұрын

if ur trying docker, make sure it is version 4.29+, as host network driver (for mac) revealed there as a beta feature

@mrdave5500 27 күн бұрын

Woot woot! great stuff. Nice easy tutorial and I now have a 'smarter' Mac. Thanks :)

@AaronHiltonSPD 27 күн бұрын

Amazing tutorial. Great stuff!

@AZisk 27 күн бұрын

Thank you! Cheers!

@kaorunguyen7782 21 күн бұрын

Alex, I love this video very much. Thank you!

@Ginto_O 25 күн бұрын

Thank you, got it to work without docker

@DaveEtchells 27 күн бұрын

I was gonna spring for a maxed M3 Max MBP, but saw rumors that the M4 Max will have more AI-related chops, so just picked up a maxed M1 Max to tide me over 😁 Really excited about setting all this up, finding this vid was very timely, thanks!

@vadim487 27 күн бұрын

Alex, you are awesome!

@marcel948 17 минут бұрын

Excellent video! Keep up!

@erenyeager655 27 күн бұрын

One thing for sure... I'll be implementing this on my menu bar for easy access :D

@moranmono 27 күн бұрын

Great video. Awesome 👏

@loveenjain 24 күн бұрын

Excellent Video giving it a try tonight on my M3 Max 14 inch model and see what are the results will share probably...

@ilkayayas 22 күн бұрын

Nice. Image generation and integrating new chatgpt in to this will be great.

@brunosanmartin1065 27 күн бұрын

These videos are so exciting for me; this channel is the number one on KZfaq. That's why I subscribe and gladly pay for KZfaq Premium. A hug, Alex!

@AZisk 27 күн бұрын

thanks for saying! means a lot

@RealtyWebDesigners 27 күн бұрын

Now we need 1TB MEMORY DRIVES (Like the Amiga used to have 'fast ram' )

@MrMrvotie 23 күн бұрын

@@AZisk Is their any chance you could incorporate a PC GPU Relative Performance Equivalence to each new apple silicon microchip that you review?

@jorgeluengo9774 26 күн бұрын

by the way, I just joined your channel, I really enjoyed these videos, very helpful, thanks!

@AZisk 26 күн бұрын

awesome. welcome!

@johnsummers7389 27 күн бұрын

Great Video Alex. Thanks.

@AZisk 27 күн бұрын

Glad you liked it!

@sungm2n 25 күн бұрын

Amazing stuff. Thank you

@bvlmari6989 27 күн бұрын

Amazing video omg, incredible tutorial man

@AZisk 27 күн бұрын

Glad you liked it!

@dibyajit9429 27 күн бұрын

I've just started my career as a Data Scientist, and I found this video to be awesome! 🤩🥳Could you please consider making a video on image generation (in LLama 3) in a private PC environment?🥺🥺

@sikarinkaewjutaniti4920 24 күн бұрын

Thx for sharing good stuff for us. Nice onec

@mendodsoregonbackroads6632 21 күн бұрын

Yes I’m interested in an image generation video. I’m running llama3 in Bash, haven’t had time to set up a front end yet. Cool video.

@guyguy467 27 күн бұрын

Thanks! Very nice video

@AZisk 27 күн бұрын

Wow! Thank you!

@BenjaminEggerstedt 26 күн бұрын

This was interesting, thanks

@OrionM42 25 күн бұрын

Thanks for the video.😊😊

@WokeSoros 17 күн бұрын

I was able to, by tracking down your Conda video, get this running. I have some web dev and Linux experience, so it wasn’t a huge chore but certainly not easy going in relatively blind. Great tutorial though. Much thanks.

@RealtyWebDesigners 27 күн бұрын

BTW - One of the BEST programmer channels!

@AzrealNimer 26 күн бұрын

I would love to see the image generation tutorial 😁

@willmartin4715 27 күн бұрын

i believe my laptop has 80 Tensor cores. for starters. This looks like a really good shift for a fri night! thanks.

@akhimohamed 26 күн бұрын

As a game dev, this is so good to have. Btw am gonna try this on parallels for my m1 pro

@Lucas-fl8ug 22 күн бұрын

You mean in windows through parallels? why would it be useful?

@Dominickleiner 21 күн бұрын

instant sub, great content thank you!

@AZisk 20 күн бұрын

Welcome aboard!

@gligoran 27 күн бұрын

Amazing video! I'd just recommend Volta over nvm.

@youssefragab2109 27 күн бұрын

This is really cool, love the channel and the videos Alex! Just curious, how is this different to an app like LM Studio? Keep up the good work!

@yuanyuanintaiwan 10 күн бұрын

My guess is that this web UI has more capabilities such as image generation which LM Studio doesn’t have. If the goal is simply to have text interaction, then I agree that this may not be necessary

@haralc 25 күн бұрын

Oh you got distracted! You're a true developer!

@shapelessed 27 күн бұрын

YO! Finally hearing of a big Svelte project! Like really, it's so much quicker and easier to ship with Svelte than others, why am I only seeing this now?

@AZisk 27 күн бұрын

Svelte for the win!

@precisionchoker 27 күн бұрын

Well.. Apple, Brave, New York times, IKEA among other big names all use svelte

@shapelessed 27 күн бұрын

@@precisionchoker But they do not acknowledge that too much..

@filipjofce 22 күн бұрын

So cool, and it's free (if we don't count the 4 grands spent for the machine). I'd love to see the images generation

@erwintan9848 26 күн бұрын

Is it fast on mac m1 pro too? How many storage used for all instalation sir? Your video is awesome!

@soulofangel1990 27 күн бұрын

Yes, we do.

@Meet7 23 күн бұрын

thanks alex

@AdityaSinghEEE 26 күн бұрын

Can't believe, I found this video today because I just started searching for Local LLMs yesterday and today, I found the complete guide. Great video Alex :)

@scorn7931 21 күн бұрын

You live in Matrix. Wake up

@keithdow8327 27 күн бұрын

Thanks!

@AZisk 27 күн бұрын

Wow 🤩 thanks so much!

@XinYue-ki3uw 26 күн бұрын

i like this tutorial, it is computer dummy friendly~

@agnemedia624 27 күн бұрын

Thanks 👍🏻

@LucaCilfoneLC 25 күн бұрын

Yes! Image generation, please!

@toddbristol707 26 күн бұрын

Great channel! I just did a build something similar with lm studio and flask based web ui. I’m going to try this method now. Btw, what was the ‘code .’ command you ran? Are you using visual studio code? Thanks again!

@AZisk 19 күн бұрын

Thanks! and thanks for joining. I did the flask thing a few videos ago, but it's just another thing to maintain. I find this webui a lot more feature rich and better looking. And yes, the 'code .' command just opens the current folder in VSCode

@ashesofasker 20 күн бұрын

Great video! So are you saying that we can get ChatGPT like quality just faster, more private and for free by running local LLM's on our personal machines? Like, do you feel that this replaces ChatGPT?

@davidgoncalvesalvarez 27 күн бұрын

My M1 Mac 16GB be real frightened on the side rn.

@blackandcold 27 күн бұрын

I ran 7b variants no problem on my now sold m1 air 16g

@ivomeadows 27 күн бұрын

got macbook with the same specs. tried to run 15b starcoder2 quantized k5m in LM studio on it, max GPU layers, getting me around 12-13 tokens per sec, not good but manageable

@RobertMcGovernTarasis 27 күн бұрын

Don't be, unless you are using other things that are super heavy as well. Llama3 8B(?) takes up about 4.7GB of Ram, with the Silicon's event use of the Nvme and Swap you'll be fine. (I prefer using LM Studio now to Ollama as it has CLI and Web built in, no need for Docker/OrbStack but, Ollama on its own without a WebUI works too)

@martinseal1987 27 күн бұрын

😂

@DanielHarrisCodes 27 күн бұрын

Great video. What format are LLM models download as? Looking into how I can use those downloaded with OLLAMA with other technologies like .NET

@Raptor235 24 күн бұрын

Great video Alex, is there anyway to have an LLM execute local shell scripts to perform tasks?

@cjchand 12 күн бұрын

Just some food for thought for future vids: Anaconda's licensing terms changed to require any org > 200 employees to license it. For this reason, many Enterprises are steering their devs away from Anaconda. Would be helpful if the tutorials used "vanilla" Python (e.g.: venv) unless Conda were truly necessary. Thanks for the vids and keep up the great work!

@AZisk 12 күн бұрын

good to know. thanks

@pixelplay1098 27 күн бұрын

Amazing stuff as Usual. Now make a tutorial on Automatic 1111

@ontime8109 25 күн бұрын

thanks!

@reyaustineechavez9600 2 күн бұрын

This hungs up my M1 Air everytime I gave a prompt Lol

@matteobottazzi6847 27 күн бұрын

A video on how you could incorporate these LLMs in your applications would be super interesting! Let's say that in your application you have a set of pdfs or html files that provide documentation on your product. If you let these LLMs analyse that documentation, then the user could get very useful information just asking and not searching through all of the documentation files!

@FelipeViaud 26 күн бұрын

@neoqe6lb 6 күн бұрын

Ollama has api endpoints that you can integrate in your apps. Check their documentation.

@jakubpeciak429 24 күн бұрын

Hi Alex, I would like to see the image generation video

@yianghan751 25 күн бұрын

Alex, excellent video! Can my MacBook air m2 with 16G RAM host these AI engines smoothly?

@innocent7048 27 күн бұрын

Here you have a super like - and a cup of coffee 🙂

@AZisk 27 күн бұрын

Yay, thank you! I haven't been to Denmark in a while - beautiful country.

@MohammedAraby 19 күн бұрын

Well be happ to see a tutorial for automatic 1111 ❤

@Mikoaj-ie6gt 25 күн бұрын

very intresting

@cookiebinary 24 күн бұрын

Tried llama3 on 8GB ram M1 :D ... I guess I was too optimistic

@kdnz_music 5 күн бұрын

Just install LM Studio and get any model and good native ui in a couple clicks

@thevirtualdenis3502 21 күн бұрын

Thanks ! Is Macbook air enough for that?

@99cya 27 күн бұрын

Hey Alex, would you say Apple is in a very good position when it comes to AI and the required hardware? So far Apple has been really quiet and lots of ppl dont think Apple can have an edge here. Whats your thought in general here?

@gayanperera7273 27 күн бұрын

Thanks @Alex, by the way is there a reason it can only use GPU, any reason not taking advantage of NPUs ?

@rickymassi 27 күн бұрын

Why not doing a deployment with Electron, so you have a desktop application. Btw I love this thing!!!

@faysal1991 18 күн бұрын

lets do some image generation please it would be super helpful

@zorawarsingh11 24 күн бұрын

Yes do images please 🙏🏻

@bisarothub1644 15 күн бұрын

Great video. But I think Jan AI is a lot easier to configure and setup for mac users

@OlegShulyakov 22 күн бұрын

When there will be a video to run LLM on an iPhone or iPad? Like using LLMFarm

@truenetgmx 27 күн бұрын

now benchmark it vs mac air :) also wonder how much these are usefull tools and not just toys

@jehad4455 27 күн бұрын

Mr. Alex Ziskind Could you clarify whether training deep learning models on a GPU for the Apple Silicon M3 Pro might reduce its lifespan? Thank you.

@jorgeluengo9774 26 күн бұрын

Thank You Alex, amazing video, I followed all steps and I enjoyed the process and the results with my m3 max. I wonder if there is a GPT that we can use from the laptop and have searches online since the cutoff knowledge date of these models seem to be over a year ago or more. For example when I ask questions of what is the terraform provider version for aws or other type of platform, is old and there is a potential to have deprecated code responses. What do you recommend in this case? not sure if you have already a video for that lol.

@AZisk 26 күн бұрын

that’s a great question. you’ll need to use a framework like flowise or langchain to accomplish this I believe, but i don’t know much about them - it’s on my list of things to learn

@jorgeluengo9774 26 күн бұрын

@@AZisk makes sense, I will do some research about it and see what I can find out to test but I will look forward when you share a video with this type of model orchestration, will be fantastic.

@113bast 27 күн бұрын

Please show image generation

@MW-mn1el 27 күн бұрын

I use Ollama with Continue plugin with VSCode. And Chatbox GUI when not code related. Work well with both Mac and Linux with Ryzen 7000 CPU. On linux it's running in a podman(docker) container. But best experience is with MacBook Pro, apple silicon and unified memory make it speedy.

@uwegenosdude 7 күн бұрын

Thanks for the video. I tried to download the code companion. Do you know why when the download of this LLM is going on, happens an upload of a couple of GBytes?

@tyron2854 27 күн бұрын

What about a new M4 iPad Pro video?

@sergey_c 25 күн бұрын

Было бы здорово ещё дать краткое описание каждой из моделей и рейтинг популярности или узконаправленности. А то установишь какие-то неизвестные модели себе на мак)

@AlexLaslau 23 күн бұрын

MBP M1 Pro with 16GB of RAM would be enough to run this?

@ChiliadStudios 2 күн бұрын

please make a video on how to run huggingface models on this thing. i cant for the life of me figure it out. such a headache

@aaronsayeb6566 21 күн бұрын

do you know if any llm would run on base model M1 MacBook Air (8GB memory)?

@nimahakimi597 27 күн бұрын

My bro. 9k views 1k likes. Beautiful ❤

@RealtyWebDesigners 27 күн бұрын

Best channel for REAL computer users - Others are just, look how fast I can compile 'VIDEOS' about doing 'videos' - Retards.

@thetabletopskirmisher 24 күн бұрын

What advantage does this have over using LM Studio that you can install directly as an app instead of using the Terminal? (Genuine question)

@justintie 26 күн бұрын

the question is: are opensource LLMs just as good as say chatGPT or Gemini?

@MeinDeutschkurs 27 күн бұрын

Without a mug, I could not do all of this. Nice to see that you also need a mug while doing all of these tasks. 🎉 #adictedTOmugs

@AZisk 27 күн бұрын

So true!

@MeinDeutschkurs 27 күн бұрын

@@AZisk 😆🤗 yeah!

@rajvanshmalhotra931 4 күн бұрын

Hey I have mac m2 normal one I want to use it for ml and dl is it possible to use it ? The normal way or should I do all my work on colab ?

@sitrakaforler8696 26 күн бұрын

Letzzzz gooooo

@ToddyIvon 27 күн бұрын

just setup my last night

@joaquincaballero4353 24 күн бұрын

Image generation video please

@bekagelashvili2904 15 күн бұрын

easy question, if i am not developer, what's the benefit i get from installing LLM in my apple silicon, what's the difference, between free version, or paid version of ai models ?

@swapwarick 27 күн бұрын

I am running llama, code Gemma on my laptop for local files intelligence. It's slow but damm it reads all my PDFs and give perfect overview

@devinou-programmationtechn9979 27 күн бұрын

Do you do it through ollama and open webui ? I m curious as to how you can send files to be processed by llms

@ShakeAndBakeGuy 27 күн бұрын

@@devinou-programmationtechn9979 GP4All works fairly well with attachments. But I personally use Obsidian as a RAG to process markdown files and PDFs. There are tons of plugins like Text Generator and Smart Connections that can work with Ollama, LM Studio, etc.

@TheXabl0 27 күн бұрын

Can you describe this “perfect overview”? Just curious what you mean by

@swapwarick 27 күн бұрын

Yes running open webui for llama and code Gemma llms on windows machine. Running open webui on localhost gives textarea where you can upload the file. The upload takes time. Once it is done, you can ask questions like give me an overview of this document, tell me all the important points of this document etc

@TheChindoboi 22 күн бұрын

Gemma doesn’t seem to work well on Apple silicon

@rafaelcordoba13 27 күн бұрын

Can you train these local LLMs with your own code files? For example adding all files from a project as context so the AI suggests things based on your current code structure and classes.

@dmitrykomarov6152 20 күн бұрын

Yeap, you can then make a RAG with the LLMs you prefer. Will be making my own RAG with llama3 this weekend.