Duong Le
Duonglv
AI & ML interests
None yet
Recent Activity
new activity about 3 hours ago
Qwen/Qwen3.8-27B:Qwen3.8-flash-next size? new activity about 5 hours ago
Qwen/Qwen3.8-27B:Any plan for Qwen4? liked a model 1 day ago
gittensor-model-hub/Qwen3.8-27B-NVFP4-RTX5090Organizations
None yet
Qwen3.8-flash-next size?
🤗 2
2
#170 opened about 4 hours ago
by
Duonglv
Any plan for Qwen4?
4
#165 opened 1 day ago
by
Duonglv
FP8 or NVFP4 quantization, please
1
#27 opened 1 day ago
by
Duonglv
Failed with repeated words
#15 opened 3 days ago
by
Duonglv
Qwen 3.8 27b wins?
👍 2
3
#14 opened 4 days ago
by
Tdamre
NVFP4 or FP8 version, please
#14 opened 4 days ago
by
Duonglv
The 27B and 35B-A3B are like the King and Queen
👀❤️ 32
3
#133 opened 7 days ago
by
Duonglv
Vietnamese parsing
2
#14 opened about 1 month ago
by
Duonglv
NVFP4 version, please
1
#12 opened 9 days ago
by
Duonglv
Qwen3.8 35B A3B model, please, please, please.
🚀❤️ 63
8
#43 opened 11 days ago
by
Duonglv
There is no --language-model-only?
#40 opened 11 days ago
by
Duonglv
So fast and great. Thank so muchhhh.
1
#3 opened 11 days ago
by
Duonglv
Can it be reduced much further?
👍 1
1
#4 opened 11 days ago
by
Duonglv
Welcome the new kinggggg
❤️ 1
#4 opened 11 days ago
by
Duonglv
Fp8 / Nvfp4 quantization, please
#12 opened 12 days ago
by
Duonglv
Small models are benchmark for the algorithm
❤️ 2
1
#21 opened 12 days ago
by
Duonglv
Dense and Moe models please!
👍 2
2
#37 opened 15 days ago
by
Duonglv
Greatttt, thank Meta. Please quantize NVFP4.
🚀 3
#17 opened 15 days ago
by
Duonglv