Democratize AI: turn $95 AMD APU into a 16GB VRAM GPU AI workhorse. Demo of AI app. stable diffusion

great work , chief

Ultra helpful video, I've been waiting to confirm this 'list of tested applications!' You know about minu pc's right? Cheapest build, least hassle, and more power efficent!

Has this been tested with LLMs? Where is the best place to find more people trying this?

dude the info is good and all but you need to consolidate the info in a single video, like it is right now is a huge mess D:

Hi, i'm using Ryzen 4650G CPU (same Vega 7 iGP as 4600G), with Ubuntu 22.04 and ROCm 5.4.2, HSA_OVERRIDE_GFX_VERSION=9.0.0 . all installation is successfull, but all generated image are black. do you know what's wrong with it? i'm also trying ROCm 5.6, but it gives me error about HIP kernel and checkpoint model did'nt loaded successfully

Thank you for this insightful tip. Maybe help out and make a bit of money by providing a list of affiliate links to all the parts in this build? Everybody that watches this video is going to want to see the parts used and some will use your links to purchase.

That is interesting, can it be used for gaming? I am looking forward to buy new budget PC and if this would be possible for gaming, that would be hell of a deal

i'm looking at your terminal, it's still using torch 1.13 + ROCm 5.2 , i think if you updated with torch 2.0 + ROCm 5.6 it'll give 10-15% performance boost (maybe more, since 10-15% boost is for ROCm 5.6 when upgrade from 5.5)

888 subscribers. yay !

Now lets wait for Quad memory channel next gen BIG APUs, some leaks show AMD developing them but only for mobile market. Depends to configuration you will have 256GB RAM and 128GB for iGPU possible.

just wondering, if i have 128GB of RAM, and utilizing 50% to iGPU, so i'll have 64GB of "iGPU VRAM" right? With this i think train SDXL or LLM will be much much cheaper (although it's slower) than nVidia (which need at least A100 to achieve similar VRAM size)

That's pretty awesome! Love to see it. We've been testing different hardware as well, I hope to post a video soon about it

Meanwhile, I'm just simply use DirectML version of Stable Diffusion. It just really works on AMD iGPUs. No hacker-level tricks, just configure the iGPU to the bigger VRAM and set up the Stable Diffusion DirectML version.

Although it works, but slow, at least little bit faster than running it on the CPU. It needs at least 8GB of VRAM and of course, you will need at least 32GB of system RAM modules installed on your computer.

@tech-practice9805 Will this work with 4650G? You mentioned Asrock board, any chance it will work on any of the Asus motherboard?

I'd love for ROCm to be integrated into TrueNAS Scale
I'd love to use my 7950x file server's iGPU to not only transcode live TV for Plex(for playack only, long term storage CPU is way better than GPU when going from MPEG2 to H265 and AV1), but also for image recognition through something like PhotoPrism

Dont get me wrong, the 7950x is an amazing CPU i can record and transcode in real time 6 channels while using only 75w at the socket using Plex DVR and TDARR with X265 CPU transcoding for ~1-2rd to 1/5th file size depending on efficiency of source.

How to install those AI models?

Thanks for the smart method :)

This is really great! Thanks for sharing...

Good to know that my work laptop m1 max is amazingly good with AI

Good video. Would be better without the loud background music.

what is the motherboard and its bios version ?

3400G?

So you are saying we can game on iGPUs now on CPUs from both Intel and AMD or just AMD alone? Like playing old console games on PS1 (Duckstation) /PS2 (PCSX2) /PS3 (RPCS3) emulators on Desktop PC?

will that work with similar Mobile APU like ryzen 4500u or R7 5700u ?

What we do with this AI application ? earning money ?

Thanks A.I. will leap forward with inovations like this

is this work for LLaMa 2 - 13B?

From what I understand, it takes 16GB out of the box, right? Did you need to configure any kernel boot parameters for that?

deserve a subscribe

waste of money and time. you're way better off buying modded 3060/3070 with 12GB/16GB VRAM from taobao for around 200 bucks

can you game with this?

Does SDXL work on CPU ?

Thanks for putting in the effort.

I think if AI is to be democratised then AMD need to step up their game. It is simply an inferior experience compared to using Nividia. You cannot expect the average consumer to install Linux, clone some github repository to run a local model and download all the required packages from scratch. Until that is easier than paying for api access to gpt plus then it will be hands of these companies.

thanks for sharing with us