FREE Local LLMs on Apple Silicon | FAST!
VloĆŸit
- Äas pĆidĂĄn 9. 05. 2024
- 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
đ Gear Links đ
* đđ„ New MacBook Air M1 Deal: amzn.to/3S59ID8
* đ»đ Renewed MacBook Air M1 Deal: amzn.to/45K1Gmk
* đ§âĄ Great 40Gbps T4 enclosure: amzn.to/3JNwBGW
* đ ïžđ My nvme ssd: amzn.to/3YLEySo
* đŠđź My gear: www.amazon.com/shop/alexziskind
đ„ Related Videos đ„
* đ RAM torture test on Mac - âą TRUTH about RAM vs SSD...
* đ ïž Host the PERFECT Prompt - âą Hosting the PERFECT Pr...
* đ ïž Set up Conda on Mac - âą python environment set...
* đ ïž Set up Node on Mac - âą Install Node and NVM o...
* đ€ INSANE Machine Learning on Neural Engine - âą INSANE Machine Learnin...
* đ° This is what spending more on a MacBook Pro gets you - âą Spend MORE on a MacBoo...
* đ ïž Developer productivity Playlist - âą Developer Productivity
đ AI for Coding Playlist: đ - âą 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
- - - - - - - - -
â€ïž SUBSCRIBE TO MY CZcams CHANNEL đș
Click here to subscribe: / @azisk
- - - - - - - - -
Join this channel to get access to perks:
/ @azisk
- - - - - - - - -
đ± ALEX ON X: / digitalix
#machinelearning #llm #softwaredevelopment - VÄda a technologie
This channel is the gift that keeps on giving.
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.
I really like that you showed the non-docker install first. I think too many rely on docker black-boxes. I prefer this. Thanks!
Dockers are not a black-box. You can get it in them, and change stuff!!!
Respectfully, Docker need not be a black box. Donât be afraid to tinker and dig in. :) But I get how doing it manually forces you to touch different parts.
Great video Alex! yes please make videos on image generation!
Thanks Alex for videos like this đ
I would like to see Image generation follow up video đ
This channel is going to be growing so fast; you make great videos that are very helpful!
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.
Great video!! And yes, please add a video explaining how to add the images generator.
These videos are so exciting for me; this channel is the number one on CZcams. That's why I subscribe and gladly pay for CZcams Premium. A hug, Alex!
thanks for saying! means a lot
Now we need 1TB MEMORY DRIVES (Like the Amiga used to have 'fast ram' )
@@AZisk Is their any chance you could incorporate a PC GPU Relative Performance Equivalence to each new apple silicon microchip that you review?
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.
Very interesting, will definitely be trying this when I get a little downtime!
Awesome thing waiting for more videos on the way
Thank you, got it to work without docker
if ur trying docker, make sure it is version 4.29+, as host network driver (for mac) revealed there as a beta feature
Woot woot! great stuff. Nice easy tutorial and I now have a 'smarter' Mac. Thanks :)
Excellent Video giving it a try tonight on my M3 Max 14 inch model and see what are the results will share probably...
One thing for sure... I'll be implementing this on my menu bar for easy access :D
Amazing tutorial. Great stuff!
Thank you! Cheers!
Alex, I love this video very much. Thank you!
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 đ
Really excited about setting all this up, finding this vid was very timely, thanks!
Great video Alex, is there anyway to have an LLM execute local shell scripts to perform tasks?
Yes Iâm interested in an image generation video. Iâm running llama3 in Bash, havenât had time to set up a front end yet. Cool video.
I've just started my career as a Data Scientist, and I found this video to be awesome! đ€©đ„łCould you please consider making a video on image generation (in LLama 3) in a private PC environment?đ„șđ„ș
Nice. Image generation and integrating new chatgpt in to this will be great.
Is it fast on mac m1 pro too?
How many storage used for all instalation sir?
Your video is awesome!
I would love to see the image generation tutorial đ
by the way, I just joined your channel, I really enjoyed these videos, very helpful, thanks!
awesome. welcome!
My M1 Mac 16GB be real frightened on the side rn.
I ran 7b variants no problem on my now sold m1 air 16g
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
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)
đ
Great video. What format are LLM models download as? Looking into how I can use those downloaded with OLLAMA with other technologies like .NET
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?
Svelte for the win!
Well.. Apple, Brave, New York times, IKEA among other big names all use svelte
â@@precisionchoker But they do not acknowledge that too much..
Great Video Alex. Thanks.
Glad you liked it!
I was able to, by tracking down your Conda video, get this running.
I have some web dev and Linux experience, so it wasnât a huge chore but certainly not easy going in relatively blind.
Great tutorial though. Much thanks.
Amazing stuff. Thank you
Great video. Awesome đ
i believe my laptop has 80 Tensor cores. for starters. This looks like a really good shift for a fri night! thanks.
Alex, excellent video!
Can my MacBook air m2 with 16G RAM host these AI engines smoothly?
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!
good to know. thanks
Alex, you are awesome!
Thanks! Very nice video
Wow! Thank you!
Amazing video! I'd just recommend Volta over nvm.
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?
Amazing video omg, incredible tutorial man
Glad you liked it!
As a game dev, this is so good to have. Btw am gonna try this on parallels for my m1 pro
You mean in windows through parallels? why would it be useful?
Thx for sharing good stuff for us. Nice onec
Thanks @Alex, by the way is there a reason it can only use GPU, any reason not taking advantage of NPUs ?
Thanks for the video.đđ
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?
This was interesting, thanks
Great channel! I just did a build something similar with lm studio and flask based web ui. Iâm going to try this method now. Btw, what was the âcode .â command you ran? Are you using visual studio code? Thanks again!
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
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.
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!
My guess is that this web UI has more capabilities such as image generation which LM Studio doesnât have. If the goal is simply to have text interaction, then I agree that this may not be necessary
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
Hi Alex, I would like to see the image generation video
MBP M1 Pro with 16GB of RAM would be enough to run this?
What advantage does this have over using LM Studio that you can install directly as an app instead of using the Terminal? (Genuine question)
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 ?
Thanks!
Wow đ€© thanks so much!
Oh you got distracted! You're a true developer!
Thanks ! Is Macbook air enough for that?
When there will be a video to run LLM on an iPhone or iPad? Like using LLMFarm
Yes, we do.
How do I find out about the hardware requirements like RAM, disk space, GPU?
thanks alex
instant sub, great content thank you!
Welcome aboard!
Here you have a super like - and a cup of coffee đ
Yay, thank you! I haven't been to Denmark in a while - beautiful country.
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 :)
You live in Matrix. Wake up
should i upgrade from macbook pro 2020 (intel core i5 8th gen quad-core 1.4ghz) to macbook air m3 15 inch for coding?
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!
+1
Ollama has api endpoints that you can integrate in your apps. Check their documentation.
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?
BTW - One of the BEST programmer channels!
i like this tutorial, it is computer dummy friendly~
do you know if any llm would run on base model M1 MacBook Air (8GB memory)?
Tried llama3 on 8GB ram M1 :D ... I guess I was too optimistic
Yes! Image generation, please!
Which model is good for programing on JavaScript no a Apple Silicon 16GB?
Thanks đđ»
Amazing stuff as Usual. Now make a tutorial on Automatic 1111
How does the MBP performance compare to Intel x Nvidia when running these local LLM
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.
thatâs a great question. youâll need to use a framework like flowise or langchain to accomplish this I believe, but i donât know much about them - itâs on my list of things to learn
@@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.
Please show image generation
the question is: are opensource LLMs just as good as say chatGPT or Gemini?
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 ?
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.
Yeap, you can then make a RAG with the LLMs you prefer. Will be making my own RAG with llama3 this weekend.
thanks!
Alex why M1 Mac getting heated when use like 10 minutes?
Why not doing a deployment with Electron, so you have a desktop application. Btw I love this thing!!!
What about a new M4 iPad Pro video?
Hi, please please, if possible to generate images through ollama webui
Is mps available on docker for Apple Silicon already?
Can someone tell me how is it different from LM studio, Anything LLM or using Lamafile? I get a bit confused with all these. Also can I make this to run with RAG?
How do we get the models updated regularly?
great job, I had some issues with finding the backend directory (it was missing) and the node thing ... btw Ollama is great
Can you make stock trading "AI" using these tools on apple or snap dragon/similar?
now benchmark it vs mac air :) also wonder how much these are usefull tools and not just toys
I've ran the phi3 model on my windows laptop and it is running on the CPU. How do I switch it to run on the GPU??
Well be happ to see a tutorial for automatic 1111 â€
Curious with all Xcode, all the models, docker, along with video editing, etc how much disk space does your system have? Are you using external drives? Trying balance ease of having plenty of drive vs Apple drive costs.
An external OWC Thunderbolt enclosure and an nvme 1-2 TB is what I went with. I use it as my boot drive and use the internal as a backup now. I run everything off of it, and I have tons of room to spare. Has to be a true thunderbolt enclosure to boot from however.
@@ghost-user559thanks. Iâll probably still boot from mac and have multiple fast drives for large data (videos, photos, models, etc)
@@ScottSquires Yeah I did that for almost a year myself. But ultimately I realized that many of my apps like Ai apps and music libraries for Logic Pro which take up hundreds of GB and I was having issues with permissions on files externally. For normal data this isnât an issue, but, many apps I use only store data in the local directory so the only way to run them is from the Boot Drive. As long as you only need storage in general then your plan works really well. But if you want to work on files regularly on that drive itâs easier to just install MacOS directly onto the external.
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
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
Do you do it through ollama and open webui ? I m curious as to how you can send files to be processed by llms
@@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.
Can you describe this âperfect overviewâ? Just curious what you mean by
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
Gemma doesnât seem to work well on Apple silicon
lets do some image generation please it would be super helpful
Image generation video please