DarkArtsForge/huihui-ai_Huihui-GLM-4.5-Air-abliterated-Q3_K_M-GGUF

110B • Updated May 22 • 107

Note My favorite model for local dataset generation. If you have more than 64GB RAM you can use Q4_K_M from concedo/Huihui-GLM-4.5-Air-abliterated-lossytensors.

mlabonne/gemma-3-27b-it-abliterated

Image-Text-to-Text • 27B • Updated Mar 21, 2025 • 2.96k • • 333

Note Best for complex system prompts. Similar quality to GLM 4.5 Air but slower. G3 and even G2 are better than G4 at following system prompts without polluting it with tons of purple prose and repetitive slop.

TheDrummer/Fallen-Command-A-111B-v1

111B • Updated Mar 24, 2025 • 5 • 26

Note Recommended IQ2_XXS for offloading. Insert the output of this model into the < think > tags of newer models to create "fallen" versions of them.

coder3101/Skyfall-31B-v4.2-heretic

31B • Updated Jun 2 • 124 • 1

Note Currently better than most 24B merges and finetunes

SicariusSicariiStuff/Assistant_Pepe_8B

266k • Updated May 3 • 414 • 74

Note 8B is more stable than 32B or 70B on my system. Great for producing unhinged output.

EldritchLabs/MN-12B-Mag-Mell-R1-Uncensored-Scale1.2

Text Generation • 12B • Updated Mar 5 • 186 • • 8

Note Best for when all else fails

TheDrummer/Tiger-Gemma-9B-v3

9B • Updated Oct 4, 2024 • 26 • 61

Note Mostly obsolete now except for low VRAM agentic use. Better than Gemma 3 12B in my tests. IQ3_S fits entirely on 8GB VRAM. Tiger 9B works surprisingly well for system prompts. Better than G4 26B at system prompt adherence.