Johny Gemstan
gemstonebro
AI & ML interests
None yet
Recent Activity
new activity 2 days ago
zai-org/GLM-5.2:How much vram needed for 1mil context minimum in total with everything? new activity 2 days ago
krea/Krea-2-Turbo:Most difficult challenge for devs new activity 8 days ago
Qwen/Qwen-Image-2512:Skill issue.... dont read!Organizations
None yet
How much vram needed for 1mil context minimum in total with everything?
7
#30 opened 5 days ago
by
gemstonebro
Most difficult challenge for devs
1
#13 opened 2 days ago
by
gemstonebro
Skill issue.... dont read!
#27 opened 8 days ago
by
gemstonebro
Question about reprompt feature
1
#7 opened 9 days ago
by
gemstonebro
I'm confused (v4 Flash vs v3.2)
4
#37 opened about 1 month ago
by
MateoTeo
Wait..where is the workflow?
1
#6 opened 12 days ago
by
gemstonebro
How to make this model work? im very tired and frustrated...
1
#50 opened 16 days ago
by
gemstonebro
Check in here for tok/s and benchmarks for local gguf models
๐ 1
6
#1 opened 5 months ago
by
ykarout
Model load in gpu & ram but only CPU compute is used
1
#27 opened 3 months ago
by
klaasb123
You guys should be proud!
#3 opened 19 days ago
by
gemstonebro
What is the eula?
1
#16 opened 25 days ago
by
gemstonebro
how do people use this thing?
1
#41 opened 21 days ago
by
gemstonebro
Qwen3.7 27B without overthinking
6
#38 opened about 1 month ago
by
Duonglv
the worst llm ive seen
#38 opened 22 days ago
by
gemstonebro
Confusing info..
4
#81 opened about 1 month ago
by
gemstonebro
Very impressive!
๐ 2
2
#40 opened 5 months ago
by
kirjolohi
Flux 2 Klein 9B ignores all {} and | in prompts.
๐ 1
5
#17 opened 6 months ago
by
a2024a
Z-image-144Celebrities dynamic prompts you can try
๐ฅโค๏ธ 2
4
#19 opened 5 months ago
by
YOUARECOOL
What is the best settings for this model? CGF, Sampler, Scheduler, Sampling Steps?
๐ 5
3
#12 opened 5 months ago
by
mrmaq01