🌌 Vega thingies.

CNWPlayer

CNWPlayer

·

AI & ML interests

SLMs, LLMs, really anything that ends in LM.

Recent Activity

new activity 1 day ago

burner22/numbat:my ass itches

new activity 1 day ago

burner22/numbat:Beware of this model, Hugging Face automatically reports 6.8T parameters, while the uploader claims approximately 14T.

reacted to inflatebot's post with 🔥 3 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!!!

View all activity

Organizations

None yet

upvoted 2 collections 3 months ago

Unsloth Dynamic 3.0 Quants

Introducing Dynamic V3.0 quants, our new SOTA quantization methodology. • 10 items • Updated 5 days ago • 105

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 43 items • Updated 6 days ago • 271

upvoted an article 3 months ago

Article

Security incident disclosure — July 2026

system

•

Jul 16

• 812