Please quantize a Q5_K_S version
#9
by
fakezeta
- opened
The performance gain going Q5 usually is worth the extra bpw from Q4_K_L: could you kindly quantize with your UD 2.0?
Or the provided Q4_K_XL should have the same performance of Q5_K_S?
Thank you
Thanks for the suggestion we'll see what we can do :)
Q4 XL should be very similar to Q5 yes