Steve Li

CHNtentes's activity

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

New activity in unsloth/Qwen3.5-9B-GGUF 1 day ago

Massive clipping damage? Why is Q8KXL have F16 tensors/layers when it's a native BF16 model?

👍 1

8

#3 opened 1 day ago by

rkh661

New activity in Qwen/Qwen3.5-35B-A3B 5 days ago

Is `qwen3_nonthinking.jinja` available for disabling thinking?

7

#23 opened 6 days ago by

kraftDong

New activity in unsloth/Qwen3.5-35B-A3B-Experiments-GGUF 5 days ago

what's this?

11

#1 opened 5 days ago by

Simon716

New activity in Qwen/Qwen3.5-35B-A3B 6 days ago

Quantization AWQ INT4

1

#17 opened 6 days ago by

abbas381366

数字和中文之间多了空格，在某些场景下完全用不了。

9

#15 opened 6 days ago by

waxwax0099

New activity in unsloth/Qwen3.5-35B-A3B-GGUF 6 days ago

Update: Should now be Fixed - Bug in UD-Q4_K_XL recipe using MXFP4 for attn tensors and experts?

👍 8

26

#5 opened 7 days ago by

ubergarm

New activity in Qwen/Qwen3.5-122B-A10B 6 days ago

Official FP8

👀 👍 14

4

#4 opened 8 days ago by

retowyss

New activity in unsloth/Qwen3.5-35B-A3B-GGUF 7 days ago

llama cpp Error: Unknown (built-in) filter 'items' for type String

9

#2 opened 8 days ago by

fullstack

New activity in unsloth/Qwen3.5-122B-A10B-GGUF 7 days ago

Multimodality not working

3

#4 opened 7 days ago by

meganoob1337

New activity in unsloth/Qwen3.5-35B-A3B-GGUF 7 days ago

Prompt cache not working correctly

👀 👍 6

1

#4 opened 7 days ago by

guiopen

New activity in Qwen/Qwen3.5-122B-A10B 7 days ago

Will there be an Instruct version?

3

#6 opened 7 days ago by

a-r-c

New activity in Qwen/Qwen3.5-35B-A3B 7 days ago

Instruct mode metrics

2

#3 opened 8 days ago by

Baskermas

New activity in Qwen/Qwen3.5-397B-A17B 14 days ago

Qwen3.5-VL 啥时候能出呢？

3

#25 opened 14 days ago by

drguolai

New activity in Qwen/Qwen3.5-397B-A17B 15 days ago

vllm 部署oom

5

#22 opened 15 days ago by

Chris2me

New activity in unsloth/MiniMax-M2.5-GGUF 18 days ago

why it's labeled as a finetune

4

#1 opened 18 days ago by

CHNtentes

New activity in MiniMaxAI/MiniMax-M2.5 19 days ago

mtp

➕ 9

2

#4 opened 19 days ago by

CHNtentes

New activity in cyankiwi/Qwen3-Coder-Next-AWQ-4bit 25 days ago

模型量化的效果并不理想

3

#2 opened 26 days ago by

mediali

New activity in unsloth/Qwen3-Coder-Next-GGUF 27 days ago

Feb 19: Qwen3-Coder-Next GGUFs update - much better outputs!

🤗 👍 16

31

#5 opened 28 days ago by

danielhanchen

New activity in stepfun-ai/Step-3.5-Flash 27 days ago

fp8 version?

1

#15 opened 27 days ago by

CHNtentes

New activity in Qwen/Qwen3-Coder-Next 29 days ago

Why no mtp layer?

👀 3

#2 opened 29 days ago by

CHNtentes