Qwen/Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 7.92M • • 19k
Mirrorize AI
risermaker
AI & ML interests
None yet
Recent Activity
reacted to inflatebot's post with 🔥 2 days ago
i am BEGGING you people to stop shoving everything in the GGUF Hole and ship w4a8/w6a8 models for ComfyUI. Comfy has bespoke kernels for these! They're fast everywhere!
4 bits should be treated as the floor for DiT weights, if you really need 3 bits or lower you should just use a different model!
Also stop shilling nvfp4 you animals!!! new activity 8 days ago
XHToken/Spark-X2.6-4B-GGUF:Incredible performance liked a model 3 months ago
Qwen/Qwen3.8-27BOrganizations
liked a
model 3 months ago
liked a
Space over 2 years ago