Update README.md
Browse files
README.md
CHANGED
|
@@ -3,8 +3,7 @@ Good story telling models that can fit in an RTX 3060 12GB. Updated March 2026.
|
|
| 3 |
# Models
|
| 4 |
|
| 5 |
- **Current favorite**: Qwen 3.5 with abliteration:
|
| 6 |
-
- [
|
| 7 |
-
- [Qwen3.5-9B-ultra-heretic](https://huggingface.co/llmfan46/Qwen3.5-9B-ultra-heretic)
|
| 8 |
|
| 9 |
At this point a roleplay finetune does more harm than good. The 27b model is very knowledgable, and the abliteration methods work perfectly.
|
| 10 |
- [zerofata/MS3.2-PaintedFantasy-v2-24B](https://huggingface.co/zerofata/MS3.2-PaintedFantasy-v2-24B) - unfortunately v3/v4/visage are cooked
|
|
|
|
| 3 |
# Models
|
| 4 |
|
| 5 |
- **Current favorite**: Qwen 3.5 with abliteration:
|
| 6 |
+
- [zerofata/G4-MeroMero-26B-A4B](https://huggingface.co/zerofata/G4-MeroMero-26B-A4B)
|
|
|
|
| 7 |
|
| 8 |
At this point a roleplay finetune does more harm than good. The 27b model is very knowledgable, and the abliteration methods work perfectly.
|
| 9 |
- [zerofata/MS3.2-PaintedFantasy-v2-24B](https://huggingface.co/zerofata/MS3.2-PaintedFantasy-v2-24B) - unfortunately v3/v4/visage are cooked
|