cong_lin1

gemlincong

·

AI & ML interests

None yet

Recent Activity

new activity 4 days ago

byteshape/Qwen3.8-27B-GGUF:have used your qwen3 and qwen3.6 MOE, if you provide a quant Qwen3.8 27B GGUF smaller than 10G, that's much better for 12G VRAM user.

liked a model 9 days ago

byteshape/Qwen3.8-27B-GGUF

new activity 9 days ago

byteshape/Qwen3.8-27B-GGUF:have used your qwen3 and qwen3.6 MOE, if you provide a quant Qwen3.8 27B GGUF smaller than 10G, that's much better for 12G VRAM user.

View all activity

Organizations

New activity in byteshape/Qwen3.8-27B-GGUF 4 days ago

have used your qwen3 and qwen3.6 MOE, if you provide a quant Qwen3.8 27B GGUF smaller than 10G, that's much better for 12G VRAM user.

#2 opened 9 days ago by

New activity in byteshape/Qwen3-30B-A3B-Instruct-2507-GGUF 8 months ago

I use this quantized model for RAG, if context is long, always get empty output

#3 opened 8 months ago by

I use this quantized model for RAG, if context is long, always get empty output

#3 opened 8 months ago by

I use this quantized model for RAG, if context is long, always get empty output

#3 opened 8 months ago by