[β]
β
bitchan
[?] help
π
host1.bitchan.one
π
@m~wzEpeV
β±
1w seen
β
0
π
0
β§
1
π hide
send βΏitcoin
[!] follow
[@] review
posts 1
/ 1
[β₯] sort oldest
β±
filter [-]
languages:
on
other
/technology
something is fucked with my setup on LM Studio (I know, I know) I'm only getting 3.5 t/s decode on Gemma 4 31b Q4_K_M at 32k context, on a 4080 with 32GB of system RAM everything is on the latest version is it because I have DDR4 RAM? Is it LM Studio? Is my shit just fucked?
β±
1w
β©