Steve Li
CHNtentes
AI & ML interests
None yet
Recent Activity
new activity
4 days ago
deepseek-ai/DeepSeek-R1-0528:Any plans for 32B/70B distilled models?
new activity
7 days ago
unsloth/DeepSeek-R1-0528-BF16:how did you produce it
liked
a model
8 days ago
deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
Organizations
None yet
CHNtentes's activity
Any plans for 32B/70B distilled models?
๐
7
3
#83 opened 7 days ago
by
NanaBanana22
how did you produce it
2
#1 opened 7 days ago
by
erichartford

Benchmarks please
10
#20 opened 9 days ago
by
Blazgo

model card ่ฟๆฒกๆดๆฐ๏ผ่ฟไธ็ๆฌๅฏไปฅๆงๅถๆ่ไน
5
#55 opened 9 days ago
by
FlintyLemming
typo in new doc?
4
#2 opened 9 days ago
by
CHNtentes
่ฟไธช้ฎ้ขๅคงๅฎถ็่พๅบๆฏไปไน๏ผ
6
#49 opened 9 days ago
by
ghostplant
I want to download BF16 weight Models, but there's not ready yet.
5
#34 opened 9 days ago
by
Robin-Han

No model card either?
7
#1 opened 9 days ago
by
oliver0102
Summer or Winter?
๐
๐
71
61
#1 opened 9 days ago
by
andromeda0302
updated version?
๐
1
#226 opened 9 days ago
by
CHNtentes
`UD-Q4_K_XL` or `Q4_K_M`?
15
#6 opened about 1 month ago
by
pootow
Is this any different from qwen official one?
4
#2 opened 25 days ago
by
CHNtentes
This model almost completely loses Chinese ablities
๐
1
3
#14 opened 26 days ago
by
CHNtentes
UD version for the Q5, Q6 and Q8 quant
๐
7
10
#11 opened about 1 month ago
by
nobita3921
Speed comparison?
#3 opened about 1 month ago
by
CHNtentes
Qwen3 is great, but could be better.
๐
7
21
#18 opened about 1 month ago
by
phil111
UPDATE FIXED! Is lower quants usable now?
3
#4 opened about 1 month ago
by
CHNtentes
UPDATED FIXED!! Template problem?
12
#2 opened about 1 month ago
by
Noonecares52647842
Is UD-Q5_K_XL better than Q5_K_M one?
2
#3 opened about 1 month ago
by
CHNtentes
Are these better than regular (non-qat) ones?
1
#1 opened about 1 month ago
by
CHNtentes