jar wladis
jarkevithwlad
AI & ML interests
None yet
Organizations
None yet
gguf please
๐ 7
4
#3 opened 2 months ago
by
jarkevithwlad
turboquant for 2 bit model https://github.com/jarkevithwlad/turboquant-prismml-cuda
โค๏ธ๐ 7
#17 opened 3 months ago
by
jarkevithwlad
thank you for the model
2
#22 opened 4 months ago
by
jarkevithwlad
256k context on rtx 3090 24gb (turboquant) used 18gb vram on Q8_0.gguf
๐ฅ 1
#43 opened 4 months ago
by
jarkevithwlad
mxfp4 ?
#1 opened 6 months ago
by
jarkevithwlad
26b-a4 version please
โค๏ธ 3
4
#9 opened 6 months ago
by
irotem98