Dämpfchen
Dampfinchen
AI & ML interests
None yet
Recent Activity
new activity
3 days ago
deepseek-ai/DeepSeek-R1-0528:Any plans for 32B/70B distilled models?
new activity
7 days ago
deepseek-ai/DeepSeek-R1-0528:This is by no means a minor upgrade.
new activity
8 days ago
deepseek-ai/DeepSeek-R1-0528-Qwen3-8B:Any plans on gemma series? ;-;
Organizations
None yet
Dampfinchen's activity
Any plans for 32B/70B distilled models?
🚀
7
3
#83 opened 7 days ago
by
NanaBanana22
This is by no means a minor upgrade.
👍
2
1
#72 opened 8 days ago
by
WyattTheSkid

Any plans on gemma series? ;-;
❤️
4
4
#2 opened 8 days ago
by
Nakdesu

DeepSeek-R1-Lite
❤️
🔥
19
7
#6 opened 8 days ago
by
Dampfinchen
fantastic 👍👍👍
🔥
2
2
#19 opened 9 days ago
by
AIARCHAEA
Distill
🔥
➕
2
5
#17 opened 9 days ago
by
Neman

In complex reasoning tasks Qwen3 is far behind QwQ
12
#32 opened about 1 month ago
by
AdamF92

Many experts seem to be underutilized, possible optimization potential.
#24 opened 29 days ago
by
Dampfinchen
repetition
➕
2
3
#23 opened 29 days ago
by
Dampfinchen
Add image visual recognition output just like qwen 2.5 vl-32b instruct
6
#26 opened about 1 month ago
by
devopsML

UD version for the Q5, Q6 and Q8 quant
👍
7
10
#11 opened about 1 month ago
by
nobita3921
Qwen3 is great, but could be better.
👍
7
21
#18 opened about 1 month ago
by
phil111
Waiting for the Qwen3-VL
👀
1
7
#8 opened about 1 month ago
by
Maverick17

Besides pruning..
6
#4 opened about 1 month ago
by
Lockout

Latest updates?
👍
12
8
#10 opened about 1 month ago
by
Dampfinchen
FIXED: Template bug fixed in llama.cpp
👍
2
7
#4 opened about 1 month ago
by
sovetboga
Great job, thanks for this model.
👍
5
4
#11 opened about 1 month ago
by
Dampfinchen
`UD-Q4_K_XL` or `Q4_K_M`?
15
#6 opened about 1 month ago
by
pootow
Feedback: It's a good model, however it hallucinates very badly at local facts (Germany)
😔
👀
9
2
#12 opened about 1 month ago
by
Dampfinchen
Is this multimodal?
1
#2 opened about 1 month ago
by
pbarker
