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

111B • Updated Mar 24, 2025 • 261 • 29

Note Deepest knowledge despite shorter outputs. Used less often than Cydonia or GLM Air due to its slow speed. However it is still my #1 favorite model of all time and can "set the tone" for other models to continue from. - For my system I use IQ2_XXS.gguf --flashattention --contextsize 8192 --gpulayers 12

BeaverAI/Cydonia-24B-v4x-GGUF

24B • Updated Oct 25, 2025 • 183 • 5

Note My #1 most used model currently, works well with SRP. Smarter than v4.3. Cyberdonia v8 is more compliant on a fresh prompt but after a few replies v4x is better. Very few refusals/disclaimers; if you need 100% uncensored outputs use Cyberdonia v8 or v11 to start, although those merges tend to become more antagonistic the more the context grows. - Stable up to 128K context using Q4_K_M, or a bit faster with 64K --contextsize 65536 --gpulayers 12

Naphula/GLM-4.5-Air-Abliterated-FQ3_K_XL-GGUF

Text Generation • 107B • Updated Aug 30 • 266 • 5

Note #2 most used. The best uncensored knowledge /speed ratio, works well with SRP and in conjunction with Cydonia. - Stable up to 32K context before hitting pagefile on my system, 16K for fully offloaded MoE

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

Image-Text-to-Text • 27B • Updated Mar 21, 2025 • 3.72k • • 346

Note Better than Gemma 4 for uncensored tasks and translations, works well with SRP. - Recommended IQ4_XS for 8GB VRAM max supported context 28K --flashattention --contextsize 28672 --gpulayers 14

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

Text Generation • 12B • Updated Mar 5 • 78 • • 14

Note Favorite 12B, works well for dataset generation, much better prose than Gemma 4. - IQ4_NL fits entirely on VRAM with 4K context