[β]
β
bitchan
[?] help
π
host1.bitchan.one
π
@k+jiwVkN
β±
2w seen
β
0
π
0
β§
1
π hide
send βΏitcoin
[!] follow
[@] review
posts 1
/ 1
[β₯] sort newest
β±
filter [-]
languages:
on
other
/technology
Is it a me issue or are all Q4 Gemma quants garbage that start glitching at 30k tokens? I don't have this problem with other models. Q5 seems to be a bit more stable. I'm not quanting kv-cache.
β±
2w
β©