CodeProject.AI: CUDA vs Apple Silicon M2

[Molbo]

I'm running BI on pretty small windows machine, that doesn't have room for a good videocard.
I want to start playing with CodeProject.AI and thinking about buying new Windows box with CUDA capable card or low end Mac mini M2 to run CP.AI on it with BI connecting to it remotely.
What would be the better solution in terms of AI performance for the same cost?
Configuration complexity is not a big deal for me and frankly, I feel myself more comfortable in UNIX-like environment.

 

[MikeLud1]

I'm running BI on pretty small windows machine, that doesn't have room for a good videocard.
I want to start playing with CodeProject.AI and thinking about buying new Windows box with CUDA capable card or low end Mac mini M2 to run CP.AI on it with BI connecting to it remotely.
What would be the better solution in terms of AI performance for the same cost?
Configuration complexity is not a big deal for me and frankly, I feel myself more comfortable in UNIX-like environment.

You might get a better answer asking your question CodeProject.AI Discussions forum Chis has be testing on all the below platforms

• Win 10 Chrome/Firefox/Edge
• Win 11 Chrome/Firefox/Edge
• Ubuntu on Raspberry Pi - Chrome
• Ubuntu via WSL Win10 and Win 11 - Chrome
• macOS (x64) Safari
• macOS (arm64) Safari

CodeProject.AI Discussions - CodeProject

www.codeproject.com

 

[wpiman]

I'm running BI on pretty small windows machine, that doesn't have room for a good videocard.
I want to start playing with CodeProject.AI and thinking about buying new Windows box with CUDA capable card or low end Mac mini M2 to run CP.AI on it with BI connecting to it remotely.
What would be the better solution in terms of AI performance for the same cost?
Configuration complexity is not a big deal for me and frankly, I feel myself more comfortable in UNIX-like environment.

Any progress on this? I have BI running on a hard metal Xeon X3, and I installed CP.AI on a Docker container on a Linux VM. No graphics card on the server. I know the Apple Silicon has dedicated hardware neural engines, but not sure that CP.AI makes use of them.

 

[Molbo]

Any progress on this? I have BI running on a hard metal Xeon X3, and I installed CP.AI on a Docker container on a Linux VM. No graphics card on the server. I know the Apple Silicon has dedicated hardware neural engines, but not sure that CP.AI makes use of them.

No progress, I don't think CPAI can use neural engines atm.