• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Get it before its gone.... Local.AI

Will be interesting to see how this fleshes out.

Screenshot_20260813-070418.pngScreenshot_20260813-070253.png
 
Needed an account for off-label usage.

The ideas behind the site are solid, it will be interesting to see how they pool data. Going to be messy at best, but should help with some insights.

1786628231021.png
 

I imagine it helps answer these questions:
Local AI is different. A model is only one part of the system. To find the best setup for your workload, you have to make several choices together.
  1. Which model suits the workload?
  2. Which hardware should run it?
  3. Which agent harness should you use?
  4. Which inference engine should serve it?
  5. Which model variation, quantization or pruning method should you use?
  6. Which runtime configuration should you choose, such as speculative decoding?
Getting the best combination should not require becoming an expert in every one of these layers.
 
  • Like
Reactions: myzz
like this
Didn't even ask just signed up.....


Looks interesting, thanks!!
 
is it a way to easily setup your own hosted AI server that you can access from the Internet ?
 
Back
Top