What GPU's you use in the Z8 G5?
JM
akierum
·
AI & ML interests
None yet
Recent Activity
new activity
about 12 hours ago
Kwaipilot/KAT-Dev:Will there be fix new proper model or jinja template fix for Roocode/Cline/Goose etc.?
Organizations
None yet
Will there be fix new proper model or jinja template fix for Roocode/Cline/Goose etc.?
#14 opened about 12 hours ago
by
akierum
Well I tried the new DevQuasar Kwaipilot.KAT-Dev.Q8_0.gguf - Lmstudio and Jan.ai errors out:
6
#9 opened 24 days ago
by
akierum
This one's great!
6
#1 opened 25 days ago
by
kbuettner
Great setup, how did you manage to connect them to cluster? What speeds do you get on 70b non moe models like KAT-DEV72B Q8 with context window 0k and 128k ?
Thanks.
the instruct following is poor
3
#9 opened 20 days ago
by
pypry
How much VRAM is required for this one
1
#1 opened 16 days ago
by
sk0d
KAT-DEV 33B no longer working with Jan.ai 0.7.2 - Cline / LMstudio v0.3.31b4 - Cline
#12 opened 9 days ago
by
akierum
Is KAT-Dev supposed to be that much slower than QWEN?
4
#11 opened 16 days ago
by
sk0d
KAT-DEV Q4 - Jan.ai - Roocode / Cline does not work Lmstudio crashes too (SOLVED)
1
#1 opened 14 days ago
by
akierum
coder vs yoyo-v4 vs thinking vs instruct in compex programming task
3
#2 opened 23 days ago
by
NIK2703
Request GGUF: Kwaipilot/KAT-Dev (62.4% (!) on SWE-Bench Verified having just 32B)
4
#15 opened 18 days ago
by
Reverger
There is new KAT-Dev-72B-Exp
9
#1 opened 22 days ago
by
akierum
This model gives errors in cline, but new official one does not
👀
1
3
#3 opened 24 days ago
by
akierum
why Kat-Dev worse then Qwen3-coder 30B?
12
#8 opened 24 days ago
by
akierum
What speed do you get at Q8 on AMD Ryzen™ AI Max+ 395
6
#14 opened 26 days ago
by
akierum
errors out with roocode
3
#1 opened 23 days ago
by
akierum
liked
a
model
23 days ago
running parameters?
👀
1
2
#5 opened about 1 month ago
by
akierum