Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Paper • 2605.21573 • Published • 110 •
4
DANIEL SOUZA
DaNS2025
AI & ML interests
None yet
Recent Activity
commentedon a paper about 19 hours ago
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models repliedto danielhanchen's post 3 days ago
Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs.
Google's new model, Gemma 4 12B Unified supports image, audio and 256K context.
You can run and train the model via Unsloth Studio.
GGUF: https://huggingface.co/unsloth/gemma-4-12b-it-GGUF
Guide: https://unsloth.ai/docs/models/gemma-4 updated a model 4 days ago
DaNS2025/MeinaMixFinal.GGUFOrganizations
None yet
commented a
paper about 19 hours ago
replied to danielhanchen's post 3 days ago
It was a bug in LM Studio. It's mentioned in the change log that it has been fixed.
updated a
model 4 days ago
published a
model 4 days ago
replied to danielhanchen's post 5 days ago
I don't think so. Models of similar size work fine. Maybe it's a bug in LM Studio, I'm not sure.
replied to danielhanchen's post 5 days ago
This won't run on anything less than 16GB. I tested it with 8GB and 12GB; you need at least 16GB to run this model(Q4) in LM Studio.
updated a
model 15 days ago
published a
model 15 days ago
liked a
model 17 days ago
liked a
model 19 days ago
liked a
model 20 days ago
liked a
model 21 days ago
Request an update to the GGUF version of "AnimaYume v05"
1
#1 opened 21 days ago
by 
btaskel
updated a
model 21 days ago
published a
model 21 days ago
bytedance-research/Lance
❤️👍 19
2
#9942 opened 24 days ago
by DaNS2025
liked a
model 24 days ago
🚩 Report: Illegal or restricted content
3
#1 opened 26 days ago
by DaNS2025
liked a
model 26 days ago
liked a
model 28 days ago