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 6 days ago
google/gemma-4-E4B-it:Image Dimension Test Results updated a model 7 months ago
Koitenshin/Nanuq-R1-14B-GGUF commentedon an article 7 months ago
Migrating the Hub from Git LFS to XetOrganizations
None yet
Image Dimension Test Results
#27 opened 6 days ago
by Koitenshin
An Improvement, But Q3 30b Still Has Very Little General Knowledge
❤️👍 3
11
#2 opened 9 months ago
by 
phil111
Any news on the awesome new benchmarks?
🚀👍 3
10
#373 opened 8 months ago
by 
VOIDER
Not Uncensored
13
#1 opened over 1 year ago
by 
SicariusSicariiStuff
Possible Improvements / Future Options
#1 opened 8 months ago
by Koitenshin
Q4_K_M is Very Unstable
#1 opened 8 months ago
by Koitenshin
Breaks once it hits Context Limit
2
#1 opened 8 months ago
by Koitenshin
Let there be light !
13
#1 opened 8 months ago
by 
phoebdroid
Comparison?
1
#5 opened 8 months ago
by 
yukiarimo
Specialized LLMs are exactly what is needed...
#1 opened 8 months ago
by Koitenshin
Hermes-Coder
❤️ 1
2
#1 opened 8 months ago
by 
Trilogix1
Model is appropriately named
2
#1 opened 8 months ago
by Koitenshin
how to make determinstic output?
4
#23 opened 9 months ago
by 
junma
Godly, but only with a Jailbreak.
#4 opened 8 months ago
by Koitenshin
Is this model vision capable?
2
#3 opened about 1 year ago
by 
lkraven
My comment
👍 1
2
#2 opened about 1 year ago
by 
Emalog
Once it admits it is wrong, it breaks
2
#7 opened 9 months ago
by Koitenshin
Content Policy Obsessed Model at Expense of Intelligence and Context Following
👍 19
31
#20 opened 9 months ago
by 
jalder1989
could you take a look at gemma3n model for your next work?
8
#1 opened 10 months ago
by 
jjwsl
Censorship sometimes appears
19
#1 opened 12 months ago
by 
Triedge