wangzilong

remember2015's activity

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

New activity in mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit 18 days ago

Convert in bf16 or fp16?

2

#2 opened 19 days ago by

remember2015

New activity in mlx-community/Qwen3-8B-4bit-DWQ-053125 19 days ago

Is there any difference in two qwen3-8b-4bit-dwq models?

#1 opened 19 days ago by

remember2015

New activity in ByteDance-Seed/Seed-X-PPO-7B 26 days ago

Amazing work, waiting for official quantized versions in MLX format

🔥 4

1

#7 opened 26 days ago by

remember2015