Compatibility check
Can I run Nemotron 3 Ultra on Apple M3 Ultra (80-core GPU)?
Yes, but only just.best quant: Q4_K_M
This one is close. The answer rests on a file size we calculated from the parameter count rather than measured, and it leaves 17.9 GB spare once the weights, a 2K context and runtime overhead are counted. A 10% error in that size changes the verdict, so treat it as a maybe and test before you buy.
Decode speed
1 tok/sest
Usable context
33K
Memory
512 GB
Q4_K_MFits in memoryest1 tok/sest · 33K ctx
Q5_K_MSpills to system RAM
Q8_0Too large
