ZhangDejun

zdjun1984's activity

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

New activity in Comfy-Org/MiniMax-H3 3 months ago

How about my RTX 3090 for running H3? Q4/Q2 or INT8 which version

6

#18 opened 3 months ago by

enwong

Speedup 4-step LoRa ?

👀➕ 18

8

#11 opened 3 months ago by

joziku

New activity in Comfy-Org/Krea-2 4 months ago

The sampling acceleration from nvfp4 quantization in Krea2 is not significant.

15

#6 opened 4 months ago by

Aca233

New activity in unsloth/Qwen3.6-35B-A3B-GGUF 6 months ago

Qwen 3.6 is much slower than Qwen 3.5 for the same quatization: UD-Q4_K_XL

10

#8 opened 6 months ago by

adr-insc

Qwen 3.6 is much slower than Qwen 3.5 for the same quatization: UD-Q4_K_XL

10

#8 opened 6 months ago by

adr-insc