zhnagchenchne/Qwen3.8-27B-GPTQ-W4A16
27B • Updated • 147 • 1
zhangchenchen
zhnagchenchne
AI & ML interests
None yet
Recent Activity
new activity 5 days ago
cyankiwi/Qwen3.8-27B-AWQ-INT4:!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! updated a model 19 days ago
zhnagchenchne/Qwen3.8-27B-GPTQ-W4A16 liked a model 21 days ago
zhnagchenchne/Qwen3.8-27B-GPTQ-W4A16Organizations
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
1
#3 opened 22 days ago
by zhnagchenchne
updated a
model 19 days ago
liked a
model 21 days ago
published a
model 21 days ago
liked a
model 24 days ago
27B where
🔥🚀 14
9
#4 opened 26 days ago
by 
pengzhi27
call vllm or sglang?
4
#2 opened about 1 month ago
by zhnagchenchne
vllm ?
1
#2 opened about 2 months ago
by zhnagchenchne
updated a
model about 2 months ago
published a
model about 2 months ago
liked a
model 9 months ago
vLLM serve for Qwen3-Omni currently only supports the thinker model.
👀 1
#8 opened 10 months ago
by zhnagchenchne
Hiding Thinking Process
2
#25 opened about 1 year ago
by 
Xzendor7
Where is the inference/vllm_tool_call.py inference/vllm_chat.py generate.py ？
2
#27 opened 12 months ago
by zhnagchenchne
What actually is the EOS token for this model?
4
#31 opened about 1 year ago
by 
jukofyork
Keep outputting empty content without stopping
2
#3 opened about 1 year ago
by zhnagchenchne
About AWQ
#3 opened about 1 year ago
by zhnagchenchne
Run 1T-param on A100/H100(80G)x8 using FP4
🚀🔥 5
7
#9 opened about 1 year ago
by 
ghostplant
onnx-community/Qwen3-Embedding-0.6B-ONNX
#25 opened about 1 year ago
by zhnagchenchne
The result is problematic.
1
#3 opened over 1 year ago
by zhnagchenchne