Does these quants support MLA?
5
#6 opened 2 months ago
by
Panchovix
IQ4_XS is optimal 4Bits model for me
#5 opened 3 months ago
by
jweb

671B params vs 685B params?
5
#3 opened 4 months ago
by
masel99

Non split version for ollama?
2
#1 opened 4 months ago
by
Martinotu