Is the KV cache of these models unusually high?
1
#6 opened 10 months ago
by
Hugsanir
prompt eval too slow
2
#4 opened 11 months ago
by
lfjmgs
can you guys share the size & perlexity tables thanks
1
#3 opened 11 months ago
by
habout632
About q4_k and q5_k
1
#2 opened 11 months ago
by
stduhpf
Cannot load model due to invalid format
2
#1 opened 12 months ago
by
ABX-AI