Quinn Comendant

datatap's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in lmstudio-community/gpt-oss-20b-MLX-8bit 5 months ago

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

👍 🔥 4

4

#1 opened 5 months ago by

datatap

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

👍 🔥 4

4

#1 opened 5 months ago by

datatap