Sebastian Schwerdhöfer

ghostwithahat's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in ibm-granite/granite-4.1-30b 2 months ago

Why no reasoning?

2

#5 opened 2 months ago by

ghostwithahat

New activity in Qwen/Qwen3.6-35B-A3B 3 months ago

My RTX 3090 ran out of excuses: Qwen3.6-35B-A3B

🔥❤️ 32

7

#37 opened 3 months ago by

Kukedlc

New activity in google/gemma-4-31B-it 3 months ago

The first small model for honest conversation

👍 7

4

#22 opened 3 months ago by

ghostwithahat

Are you insane to push agenda into local model?

🤯❤️ 19

12

#8 opened 3 months ago by

Krokozor

New activity in OrionLLM/GRM2-3b 3 months ago

Recommended Parameters?

1

#4 opened 3 months ago by

ghostwithahat

New activity in HauhauCS/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive 4 months ago

How did you uncensor this model?

7

#7 opened 4 months ago by

ghostwithahat

New activity in llmfan46/Qwen3.5-27B-ultra-uncensored-heretic-v1 4 months ago

How did you apply SOMA?

1

#4 opened 4 months ago by

ghostwithahat

New activity in YatharthS/LavaSR 4 months ago

Impressive!

1

#2 opened 4 months ago by

ghostwithahat

New activity in zai-org/GLM-4.7-Flash 5 months ago

Quantized GLM-4.7-Flash with llama.cpp and opencode.

3

#66 opened 5 months ago by

ghostwithahat

New activity in DavidAU/Qwen3-48B-A4B-Savant-Commander-Distill-12X-Closed-Open-Heretic-Uncensored-GGUF 6 months ago

Change number of experts used in llama.cpp

👍 1

1

#2 opened 6 months ago by

ghostwithahat

New activity in pszemraj/granite-4.0-h-small-heretic_hi 7 months ago

This works very well!

4

#1 opened 7 months ago by

ghostwithahat

New activity in coder3101/gemma-3-27b-it-heretic 7 months ago

Reacts weird

3

#1 opened 7 months ago by

ghostwithahat

New activity in mlabonne/gemma-3-27b-it-abliterated 7 months ago

Very good!

😎❤️ 2

1

#15 opened 7 months ago by

ghostwithahat