|
|
|
|
|
|
by coder543
780 days ago
|
|
|
4-bit is fine for models of all sizes, in my experience. The only reason I personally don’t quantize tiny models very much is because I don’t have to, not because the accuracy gains from running at 8-bit or fp16 are that great. I tried out 4-bit Phi-3 yesterday, and it was just fine. |
|
|