SUPER Cheap Ai PC - Low Wattage, Budget Friendly, Local Ai Server with Vision

Exploring the cheap end of AI we end up testing M2000 or K2200 and P2000s against CPU inference to see what local Ai performance looks like in the mid $100 price range. I thought going in it would be the K2200, but there is a twist to this so make sure you watch!

SUPER BUDGET AI RIG

RIGS, GUIDES, SOFTWARE

Chapters
0:00
0:27 Ai PC Parts
3:24 How To Start With AI Learning
4:33 K2200 on MiniCPM Vision Model
11:00 Im doubting the K2200s here
17:15 M2000 Al Testing
18:44 P2000 Testing
21:00 Conclusions

Be sure to 👍✅Subscribe✅👍 for more content like this!

Please share this video to help spread the word and drop a comment below with your thoughts or questions. Thanks for watching!

*****
As an Amazon Associate I earn from qualifying purchases.

When you click on links to various merchants on this site and make a purchase, this can result in this site earning a commission. Affiliate programs and affiliations include, but are not limited to, the eBay Partner Network.
*****

[dorinxtg]

Looking at the price: 2XP2000 will cost you around $200 (+shipping) while a new RTX 3060 12GB will cost you $284 from Amazon (+shipping), so for around $84, why should someone buy the 2 P2000 cards? I'm pretty sure that RTX3060 will smack out the dual P2000

[RoyFox-ti]

Love these videos! Keep up the great work! I currently have a gaming pc with the 4090 im using for ai inference but will be building your setups starting with this one and then moving to the midsize before the monster quad gpu one!

[Choooncey]

now that intel battlemage is out i bet they will be more price competitive with dedicated AI cores

[elliotthanford]

I would be interested to see how a tesla p4 or 2 does, especially as they are around $100 especially when compared to a 3060

[JoshuaBoyd]

I was excited that you went from k2200 to m2000 to p2000. If you would have stopped at k2200 I would have been really disappointed.

[clomok]

I have been playing with Ollama on an AMD Ryzen 5900hx with 32gb of DDR4-3200 RAM and I ran the same models (with my RAM already over 65% taken using other stuff)
And got 8-9 tokens/s with minicpm-v:8b and have been happy with the 17-19 token/s I can get with llama3.2:3b

[ebswv]

Thanks for the videos. I am looking to build a home AI server for ~$1000 or less. Would love to see a video on what you could build for around that price range.

[mitzusantiago]

Hi! I really enjoyed your video. I'm trying to do some experimental work (research) with local AI models (I'm a teacher). What is your opinion about using Xeon processors (like the ones that are sold in AliExpress) plus a graphic card like the ones that you presented? Is the Xeon processor necessary or Can I choose any other processor? (like a Ryzen plus an nvidia card). Greetings from Mexico.

[andAgainFPV]

stoked i found your channel! I'm considering using Exo to distribute a llm across my families fleet of gaming pcs, however not sure on the overall power draw. Thoughts?

[jk-mmto]

I have two titan xp's languishing. They may have a new purpose now.

[UCsktlulEBEebvBBOuDQ]

My dual P40 + A2000 use 550w at idle lol Keeps me warm

[jensodotnet]

I tested the minicpm-v:8b on a gtx 1070 ~37 t/s, and on a rtx 3090 ~92 t/s. Using this prompt: "Help me study vocabulary: write a sentence for me to fill in the blank, and I'll try to pick the correct option." ~5, 5gb vram. Default values. Tested with an image and prompt "explain the meme" using an image and got ~34t/s (gtx1070) and 97t/s (rtx 3090) the image was resized to 1344x1344

[tomoprime]

What about AMD gpus? Haven't they made progress for AI and cuda alternatives?

[SunnyCurwenator]

Sorry, a really basic question from me; puns unintended. What are you using to collect reliable stats on power consumption (watts). We have Threadrippers and we're considering a couple of 4090s, but one question relates to having good metrics on power usage at idle and peak usage. Then we can begin to track and compare power costs. What have you found that works? Thanks in advance. Sunny

[lovebutnosoilder]

Could I use a 4x x4 bifurcated pcie slot adapter and squeeze 5 gpus in the pc?

[sevilnatas]

Does the number of Cuda cores play into performance, or is it just about memory when it comes to inference? Some consumer cards have the ram numbers but their core count tends to be lower than the data center cards. Also, do the cores factor in when using multiple gpus, or again, are you just providing the system more ram?

[ChrisCebelenski]

My 16GB 4060 TI clocks in around 31 tps on this model (single card used). I've seen these for around $400 USD, so price/performance ratio is on par, but overall system price is higher. And you get 16GB of VRAM, which is going to be the limiting factor with the cheaper cards even if the performance is OK for you.

[Nettlebed]

20-80 watts? This means live 24/7 classification of persons on your Ring is not only technically feasible but also financially acceptable.

[thomaslindell]

How did you get that gpu utilization. In the text term.

[thegeekchef]

yeah I have to say I enjoy running 3x Rtx 3060 12bib cards. Pretty OK speed and space.