Sebastian Schwerdhöfer
ghostwithahat
·
AI & ML interests
None yet
Recent Activity
liked a model 21 days ago
Blackfrost-AI/Qwen3.8-27B-ABLITERATED-BF16 new activity 26 days ago
Qwen/Qwen3.8-27B:Turboquant? new activity 26 days ago
Qwen/Qwen3.8-27B:Turboquant?Organizations
None yet
Turboquant?
6
#141 opened 26 days ago
by
ghostwithahat
Why no reasoning?
2
#5 opened 4 months ago
by
ghostwithahat
My RTX 3090 ran out of excuses: Qwen3.6-35B-A3B
🔥❤️ 33
7
#37 opened 5 months ago
by
Kukedlc
The first small model for honest conversation
👍 7
4
#22 opened 5 months ago
by
ghostwithahat
Are you insane to push agenda into local model?
🤯❤️ 19
12
#8 opened 5 months ago
by
Krokozor
Recommended Parameters?
1
#4 opened 6 months ago
by
ghostwithahat
How did you uncensor this model?
7
#7 opened 6 months ago
by
ghostwithahat
How did you apply SOMA?
1
#4 opened 6 months ago
by
ghostwithahat
Impressive!
1
#2 opened 6 months ago
by
ghostwithahat
Quantized GLM-4.7-Flash with llama.cpp and opencode.
3
#66 opened 7 months ago
by
ghostwithahat
New activity in DavidAU/Qwen3-48B-A4B-Savant-Commander-Distill-12X-Closed-Open-Heretic-Uncensored-GGUF 9 months ago
Change number of experts used in llama.cpp
👍 1
1
#2 opened 9 months ago
by
ghostwithahat
This works very well!
4
#1 opened 10 months ago
by
ghostwithahat
Reacts weird
3
#1 opened 10 months ago
by
ghostwithahat
Very good!
😎❤️ 2
1
#15 opened 10 months ago
by
ghostwithahat