Quantised version
#12
by
nikhilfande
- opened
Is there any plan to release quantised version of 8B model such that it could be fit in single T4 machine? or you suggest to use 4B model in such case ?
Is there any plan to release quantised version of 8B model such that it could be fit in single T4 machine? or you suggest to use 4B model in such case ?