The is extremely slow and not useful in my opinion.
It makes the difference between being able to run a lot of machine learning tasks, and not being able at all. Pretty useful.
I would say it depends entirely on your usecase. I don't think there can be a simple "not useful" generalization that applies to everyone.
Man I wish that was a canned response that could be deployed on demand! Well said.
I really appreciate thriftful & resourceful points of view. Exploring what if, looking for use is such a great virtue.
Can you elaborate beyond the shallow/superficial dismissal?
If it takes seconds in VRAM it can take tens of minutes running the same thing offloaded to RAM if it hasn't been designed to do it.
It is about as useful as rtx
[dead]
It makes the difference between being able to run a lot of machine learning tasks, and not being able at all. Pretty useful.
I would say it depends entirely on your usecase. I don't think there can be a simple "not useful" generalization that applies to everyone.
Man I wish that was a canned response that could be deployed on demand! Well said.
I really appreciate thriftful & resourceful points of view. Exploring what if, looking for use is such a great virtue.
Can you elaborate beyond the shallow/superficial dismissal?
If it takes seconds in VRAM it can take tens of minutes running the same thing offloaded to RAM if it hasn't been designed to do it.
It is about as useful as rtx
[dead]