Koitenshin
Koitenshin
AI & ML interests
I like breaking things and playing the mad scientist. Did you know we still haven't completely untapped the full potential of SD 1.5 yet?
Recent Activity
new activity about 15 hours ago
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B:Tool calls and reasoning not reliable on llama.cpp (fix provided) liked a model 6 days ago
SL-AI/GRaPE-2.5-Helios-GGUF new activity 9 days ago
SL-AI/GRaPE-2.5-Helios-GGUF:This model is insane.Organizations
None yet
Tool calls and reasoning not reliable on llama.cpp (fix provided)
👍❤️ 16
6
#6 opened 4 days ago
by 
coder543
This model is insane.
👍 1
1
#1 opened 9 days ago
by Koitenshin
Gemma 4.2 26B A4B?
2
#58 opened about 1 month ago
by 
kozusenok
Adding `safetensors` variant of this model
🔥 4
2
#1 opened about 1 year ago
by 
SFconvertbot
Prescence penalty 1.5
👀👍 4
2
#5 opened 5 months ago
by 
Sliderpro93
The high-quality is actually pretty bad
11
#3 opened about 1 month ago
by 
I-Am-Sam
Extremely slow, but amazing
#2 opened 27 days ago
by Koitenshin
not particularly smart
👍 14
1
#7 opened 4 months ago
by 
toriset
Thanks - it works well in opencode
🤝❤️ 7
13
#1 opened 3 months ago
by 
Milor123
The model suffers from ADHD
👍 1
7
#18 opened 9 months ago
by 
Candala
What about uncensored/abliterated version?
❤️ 2
12
#2 opened 5 months ago
by 
tima2431
Image Dimension Test Results
1
#27 opened 5 months ago
by Koitenshin
An Improvement, But Q3 30b Still Has Very Little General Knowledge
👍❤️ 3
11
#2 opened about 1 year ago
by 
phil111
Any news on the awesome new benchmarks?
🚀👍 3
10
#373 opened about 1 year ago
by 
VOIDER
Not Uncensored
13
#1 opened about 2 years ago
by 
SicariusSicariiStuff
Possible Improvements / Future Options
👍 1
#1 opened about 1 year ago
by Koitenshin
Q4_K_M is Very Unstable
#1 opened about 1 year ago
by Koitenshin
Breaks once it hits Context Limit
2
#1 opened about 1 year ago
by Koitenshin
Let there be light !
13
#1 opened about 1 year ago
by 
phoebdroid