Quinn Comendant's picture

Quinn Comendant

datatap

·

https://mastodon.social/@com

AI & ML interests

None yet

Recent Activity

upvoted a collection 8 days ago

liked a model 7 months ago

rednote-hilab/dots.ocr

new activity 8 months ago

lmstudio-community/gpt-oss-20b-MLX-8bit:The base model is 4bit (“native MXFP4 quantization”), is it useful to upscale to 8bit?

View all activity

Organizations

None yet

New activity in lmstudio-community/gpt-oss-20b-MLX-8bit 8 months ago

The base model is 4bit (“native MXFP4 quantization”), is it useful to upscale to 8bit?

#1 opened 8 months ago by

The base model is 4bit (“native MXFP4 quantization”), is it useful to upscale to 8bit?

#1 opened 8 months ago by