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 3 days ago
empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Thanks - it works well in opencode new activity 28 days ago
mistralai/Ministral-3-14B-Instruct-2512:The model suffers from ADHD new activity about 1 month ago
deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:What about uncensored/abliterated version?Organizations
None yet
Thanks - it works well in opencode
❤️ 4
13
#1 opened 5 days ago
by 
Milor123
The model suffers from ADHD
👍 1
7
#18 opened 6 months ago
by 
Candala
What about uncensored/abliterated version?
❤️ 2
12
#2 opened about 2 months ago
by 
tima2431
Image Dimension Test Results
1
#27 opened about 2 months ago
by Koitenshin
An Improvement, But Q3 30b Still Has Very Little General Knowledge
❤️👍 3
11
#2 opened 11 months ago
by 
phil111
Any news on the awesome new benchmarks?
🚀👍 3
10
#373 opened 10 months ago
by 
VOIDER
Not Uncensored
13
#1 opened almost 2 years ago
by 
SicariusSicariiStuff
Possible Improvements / Future Options
👍 1
#1 opened 10 months ago
by Koitenshin
Q4_K_M is Very Unstable
#1 opened 10 months ago
by Koitenshin
Breaks once it hits Context Limit
2
#1 opened 10 months ago
by Koitenshin
Let there be light !
13
#1 opened 10 months ago
by 
phoebdroid
Comparison?
1
#5 opened 10 months ago
by 
yukiarimo
Specialized LLMs are exactly what is needed...
#1 opened 10 months ago
by Koitenshin
Hermes-Coder
❤️ 1
2
#1 opened 10 months ago
by 
Trilogix1
Model is appropriately named
2
#1 opened 10 months ago
by Koitenshin
how to make determinstic output?
4
#23 opened 11 months ago
by 
junma
Godly, but only with a Jailbreak.
#4 opened 10 months ago
by Koitenshin
Is this model vision capable?
2
#3 opened over 1 year ago
by 
lkraven
My comment
👍 1
2
#2 opened over 1 year ago
by 
Emalog
Once it admits it is wrong, it breaks
2
#7 opened 10 months ago
by Koitenshin