Duong Le
Duonglv
AI & ML interests
None yet
Recent Activity
liked a model 10 days ago
Intel/gemma-4-31B-it-int4-AutoRound new activity 10 days ago
gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090:Can Any Model Be Quantized This Way? new activity 13 days ago
google/gemma-4-E2B-it:Weak at generating structured output.Organizations
None yet
Can Any Model Be Quantized This Way?
#15 opened 10 days ago
by
Duonglv
Weak at generating structured output.
2
#47 opened 13 days ago
by
Duonglv
Multiplingual or just English and Chinese
1
#14 opened 17 days ago
by
Duonglv
Any plan for Reranker model?
#45 opened 17 days ago
by
Duonglv
Can not run with vLLM
πβ 2
4
#35 opened about 1 month ago
by
DuongLeVan
Use cases for this model
πβ 3
1
#4 opened 21 days ago
by
Duonglv
Plan for Gemma 5?
π 1
#62 opened 23 days ago
by
Duonglv
NVFP4 please!
π 1
2
#5 opened 24 days ago
by
Duonglv
What is the true ranking of this model?
π 1
7
#180 opened about 1 month ago
by
Duonglv
Does the model support multiplingual?
3
#4 opened 25 days ago
by
Duonglv
New AI = Intelligence + Knowledge
π 1
4
#43 opened 26 days ago
by
Duonglv
Dense and Moe models under 36B, please
β€οΈπ 8
#31 opened 29 days ago
by
Duonglv
Broader benchmarks
#30 opened about 1 month ago
by
Duonglv
Can see, can touch but canβt use
πβ 20
11
#4 opened about 1 month ago
by
Duonglv
Qwen4 with Various Sizes?
β€οΈ 2
1
#25 opened about 1 month ago
by
Duonglv
Qwen3.8-flash-next size?
π€ 2
2
#170 opened about 1 month ago
by
Duonglv
Any plan for Qwen4?
4
#165 opened about 1 month ago
by
Duonglv
FP8 or NVFP4 quantization, please
1
#27 opened about 1 month ago
by
Duonglv
Investigating the Trade-off between Reasoning/Efficiency and Instruction Following in Ornith-1.5
π 1
16
#26 opened about 1 month ago
by
AnbaiMei