TheDrummer/Fallen-Command-A-111B-v1
111B • Updated • 13 • 26
Favorite Models
Mostly uncensored models for low VRAM budget
Note Recommended IQ2_XXS for offloading. Even IQ1_S is viable. Insert the output of this model into the < think > tags of newer models to create "fallen" versions of them.
SicariusSicariiStuff/Assistant_Pepe_8B
266k • Updated • 307 • 69Note 8B is more stable than 32B or 70B on my system
-
DarkArtsForge/MN-Raven-12B-v1
Text Generation • Updated • 105 • 6
DarkArtsForge/Morax-24B-v2
Text Generation • Updated • 196 • 6Note Extremely morbid and deranged.
-
EldritchLabs/MN-12B-Mag-Mell-R1-Uncensored-Scale1.2
Text Generation • 12B • Updated • 13 • • 6
mlabonne/gemma-3-27b-it-abliterated
Image-Text-to-Text • 27B • Updated • 9.37k • • 330Note Best for complex system prompts
-
concedo/Huihui-GLM-4.5-Air-abliterated-lossytensors
Text Generation • 110B • Updated • 5 • 5
DarkArtsForge/huihui-ai_Huihui-GLM-4.5-Air-abliterated-Q3_K_M-GGUF
110B • Updated • 185Note best version of the above model for 64GB RAM
-
Naphula/Meme-Trix-MoE-14B-A8B-v1
Text Generation • 14B • Updated • 7 • 8
Naphula/Delirium-v1-abliterated
Text Generation • 9B • Updated • 4 • 1Note Recommend adding the deslop tokenbans from the model card
-
Naphula/Goetia-8B-v1
Text Generation • 8B • Updated • 15 • 7 -
OccultAI/Adversary-8B-v1a
8B • Updated • 25 • 3 -
Naphula/G4-Runic-Oarfish-26B-A4B-v1.2
Image-Text-to-Text • 25B • Updated • 316 • 11
TheDrummer/Tiger-Gemma-9B-v3
9B • Updated • 18 • 61Note IQ3_S fits entirely on 8GB VRAM. Tiger 9B works surprisingly well for system prompts. It was the best budget model of its time and is still my favorite Gemma 2.
Naphula/DarkForest-20B-v2.0-Erebus-Edition
20B • Updated • 8 • 11Note Creative and uncensored RP, dark and unhinged, the OG of this list