clef-flash

17 records across 4 hardware.

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
Quadro RTX 4000clef-flash Q5_K_M-dynllama.cpp (CUDA)1100–––16384–community–source
M5 Maxclef-flash 4bitoMLX100.62471.0––10242026-10-07community–source
M5 Maxclef-flash 4bitoMLX99.42816.0––40962026-10-07community–source
M5 Maxclef-flash 4bitoMLX81.52586.0––10242026-10-15community–source
M5 Maxclef-flash 4bitoMLX81.02146.0––10242026-10-15community–source
M5 Maxclef-flash 4bitoMLX80.42474.0––40962026-10-15community–source
M5 Maxclef-flash 4bitoMLX79.62837.0––40962026-10-15community–source
M5 Maxclef-flash 8bitoMLX57.23148.0––40962026-10-06community–source
M5 Maxclef-flash 8bitoMLX57.23148.0––40962026-10-06community–source
M5 Maxclef-flash 8bitoMLX55.13140.0––163842026-10-06community–source
M5 Maxclef-flash 8bitoMLX55.13140.0––163842026-10-06community–source
M6clef-flash 4bitoMLX31.91039.0––10242026-10-10community–source
M6clef-flash 4bitoMLX31.21154.0––40962026-10-10community–source
M4clef-flash 4bitoMLX21.2201.9––10242026-10-08community–source
M4clef-flash 4bitoMLX20.9240.4––40962026-10-06community–source
M4clef-flash 4bitoMLX20.5207.3––40962026-10-08community–source
M4clef-flash 4bitoMLX20.3228.0––10242026-10-06community–source

← all models