Speed up
2
#11 opened about 2 months ago
by
cute69
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/RjpFgBpeDqGJisREOwu8x.png)
You seem to have forgotten to update some of the Quants
#9 opened about 2 months ago
by
Mikael110
cpu vs gpu
#8 opened about 2 months ago
by
francescofiamingo
Will it work with ooba?
2
#5 opened 2 months ago
by
lhucklen
Q6_K response quality diverges (in a bad way)
34
#4 opened 2 months ago
by
thethinkmachine
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6628d1f30058447ca0a3824a/pdjs14Uq0_F2rB2kQof6J.jpeg)
gemma 9b with llama cpp b3259
1
#3 opened 2 months ago
by
sdyy