Phil's picture

Phil

cduk

·

AI & ML interests

None yet

Recent Activity

new activity 16 days ago

cyankiwi/Qwen3.5-27B-AWQ-4bit:How big would the model be if you quantized linear weights to 8 bits instead of 4 bits?

liked a model 17 days ago

Kbenkhaled/Qwen3.5-27B-quantized.w4a16

new activity 18 days ago

dealignai/Qwen3.5-VL-122B-A10B-4bit-MLX-CRACK:Can you make a GGUF version

View all activity

Organizations

cduk 's Spaces 2

Minilmtestv2

Minilmtest