Duong Le
Duonglv
AI & ML interests
None yet
Recent Activity
new activity about 6 hours ago
unsloth/Qwen3.6-35B-A3B-NVFP4-Fast:Can't load the model in 32G VRAM (vLLM) liked a model 2 days ago
ATH-MaaS/OvisOCR2 new activity 7 days ago
InternScience/Agents-A1:NVFP4 quantizationOrganizations
None yet
Can't load the model in 32G VRAM (vLLM)
1
#8 opened 2 days ago
by
Duonglv
NVFP4 quantization
2
#19 opened 9 days ago
by
Duonglv
What are use cases for this model?
👍 1
3
#6 opened 22 days ago
by
Duonglv
Please FUCK Anthropic
❤️🚀 136
19
#6 opened about 1 month ago
by
6cf
Qwen3.7 27B without overthinking
👍 1
6
#38 opened about 2 months ago
by
Duonglv
Multilingual or just English and Chinese
#13 opened 29 days ago
by
Duonglv
A bad output when parsing pdf in vietnamese
#7 opened 30 days ago
by
Duonglv
Stronger model for Agentic workflow
👀👍 13
4
#3 opened about 1 month ago
by
Duonglv
Please support vietnamese
#55 opened 2 months ago
by
Duonglv
Reranker model for multilingual
#2 opened 2 months ago
by
Duonglv
Overthinking model
#3 opened 2 months ago
by
Duonglv
16 - 24B models with FP8 quantization
👍 5
6
#152 opened 3 months ago
by
Duonglv
Running with vLLM as a server
8
#10 opened 3 months ago
by
Duonglv
Qwen3.6-27B-AWQ-INT4 for running in vLLM
➕ 6
2
#19 opened 3 months ago
by
Duonglv
unsloth/Qwen3.6-27B-AWQ
#20 opened 3 months ago
by
Duonglv
Model evaluations
1
#2 opened 3 months ago
by
Duonglv
Great model, please release ~16B model with FP8
2
#9 opened 3 months ago
by
Duonglv
Bigger HunyuanOCR
1
#28 opened 3 months ago
by
Duonglv
Smaller models, embedding and reranker models
❤️ 11
#18 opened 3 months ago
by
Duonglv
Qwen3.6-27B?
🚀❤️ 32
19
#2 opened 3 months ago
by
lingyezhixing