Dämpfchen
Dampfinchen
·
AI & ML interests
None yet
Recent Activity
new activity
about 18 hours ago
google/gemma-3-27b-it:Status on Gemma 4?
new activity
about 19 hours ago
Qwen/Qwen3.5-397B-A17B:Smaller GGUF without the vision weights?
new activity
1 day ago
Qwen/Qwen3.5-397B-A17B:Others model?
Organizations
None yet
Status on Gemma 4?
🔥
3
1
#100 opened about 18 hours ago
by
Dampfinchen
Smaller GGUF without the vision weights?
1
#19 opened about 22 hours ago
by
rtzurtz
Others model?
👀
3
2
#7 opened 1 day ago
by
Sashkanik13
Congratulations on this release!
🔥
12
1
#3 opened 1 day ago
by
Dampfinchen
Someone merged Turbo and SFT and it is a huge improvement in my opinion.
👀
1
#19 opened 5 days ago
by
Dampfinchen
Discussion on qualities and the ta?
👍
3
1
#1 opened 7 days ago
by
soymh
Short feedback
😎
1
1
#15 opened 10 days ago
by
Dampfinchen
fp16 is not working (Z-Image base incompatible with RTX 20 series, RDNA2 and older)
👍
1
1
#22 opened 16 days ago
by
Dampfinchen
Support for sounds?
👍
2
1
#26 opened 17 days ago
by
Dampfinchen
Congratulations on this release and on one important realization!
🔥
👍
19
5
#5 opened 21 days ago
by
Dampfinchen
Excellent model - short feedback
2
#44 opened 24 days ago
by
Dampfinchen
Why does the KV cache occupy so much GPU memory?
13
#21 opened 28 days ago
by
yyg201708
Excellent version
🔥
5
5
#19 opened 28 days ago
by
luxiangyu
guys we also need some AIR
➕
❤️
50
30
#1 opened 5 months ago
by
jacek2024
Why not experiment?
👍
1
3
#1 opened 3 months ago
by
Dampfinchen
A look into the future: Wishlist for GLM-5
👍
13
5
#2 opened 6 months ago
by
Dampfinchen
Text performance compared to GLM-4.5 Air
👀
6
3
#1 opened 6 months ago
by
Dampfinchen
Please consider making different model sizes and multimodality
👍
5
#9 opened 6 months ago
by
Dampfinchen
Kimi-K2-Mini
👍
22
15
#1 opened 7 months ago
by
PSM24
Multimodality
3
#5 opened 7 months ago
by
Dampfinchen