gokhanbuz
gbuzhf
AI & ML interests
None yet
Recent Activity
updated a model 7 minutes ago
gbuzhf/KAT-Coder-V2.5-Dev-NativeMTP-GGUF new activity about 2 hours ago
gbuzhf/KAT-Coder-V2.5-Dev-NativeMTP-GGUF:Acceptance Test Results with production parameters & harnesses updated a model about 2 hours ago
gbuzhf/KAT-Coder-V2.5-Dev-MTP-GGUFOrganizations
None yet
Acceptance Test Results with production parameters & harnesses
4
#3 opened about 4 hours ago
by
gbuzhf
I-Compact results and questions
🤝🔥 2
2
#1 opened about 22 hours ago
by
NeoHuggingF
Amazing
👍 2
2
#2 opened about 1 month ago
by
gbuzhf
What are best llamma.cpp run settings for opencode etc.?
4
#9 opened 8 days ago
by
akierum
MTP support? Why no Vision?
20
#3 opened 10 days ago
by
unoid
Really Great Job
🔥 2
#1 opened 6 days ago
by
gbuzhf
KAT-Coder-V2.5
#6 opened 10 days ago
by
gbuzhf
Is this Heretic?
#4 opened 12 days ago
by
gbuzhf
APEX Heretic
1
#1 opened 24 days ago
by
gbuzhf
What's the context size max that can be used with this one in llama.cpp?
1
#2 opened 26 days ago
by
maikelthedev
Not your traces, but distilled smaller models...
😔 1
3
#18 opened 28 days ago
by
gbuzhf
Doesnt load up - excessive ram consumption
3
#3 opened about 2 months ago
by
Pumba2
Same group runs the tests, same group publishes the best
#4 opened about 1 month ago
by
gbuzhf
Infinite thinking loop (repeating same paragraph until natural stop)
#6 opened about 1 month ago
by
gbuzhf
IQ4_NL vs. IQ4_XS
#2 opened about 1 month ago
by
gbuzhf
Having `encoding` problem with bash commands and paths all the way...
#20 opened about 1 month ago
by
gbuzhf
It is Gemma-4-E4B
➕ 1
4
#1 opened about 2 months ago
by
gbuzhf
New activity in mradermacher/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-GGUF about 1 year ago
This isn't abliterated
1
#1 opened about 1 year ago
by
gbuzhf