mradermacher/MN-Violet-Lotus-12B-GGUF

12B • Updated Nov 17, 2024 • 14.1k • 55

Note Very good model. Better than Violet Twilight. Very creative and fully uncensored, but after 20k+ context can slightly loose details.

grimjim/Magnolia-Mell-v1-12B

Text Generation • 12B • Updated Jun 1, 2025 • 187 • 3

Note Uncensored. Good narrative style.

djuna/MN-Chinofun-12B-4.1

Text Generation • 12B • Updated Jan 26, 2025 • 36 • 6

Note Uncensored. Excellent at narrative. Much better than Wayfarer imho.

Nitral-AI/Wayfarer_Eris_Noctis-12B

Text Generation • 12B • Updated Jan 26, 2025 • 20 • • 30

Note Uncensored. Good at role-play and storytelling. Personal top 5 of May 2025

grimjim/Magrathic-12B

Text Generation • 12B • Updated Jul 1, 2025 • 83 • 1

Note Good uncensored model for 1 on 1 role-play. I can't say which is better in comparison with grimjim's Magnolia-Mell-v1, but this one possibly have a little better narrative.

Vortex5/Moonlit-Shadow-12B

Text Generation • 12B • Updated Aug 18, 2025 • 33 • 6

Note Good uncensored model.

Lewdiculous/MN-12B-Lyra-v4-GGUF-IQ-Imatrix

12B • Updated Sep 10, 2024 • 7.99k • 40

Note Very good result, but slow on long play. Also not fully uncensored.

Sao10K/14B-Qwen2.5-Kunou-v1

Text Generation • 15B • Updated Dec 15, 2024 • 127 • • 32

Note Good uncensored Qwen 2.5. Love it.

Lewdiculous/L3-8B-Stheno-v3.2-GGUF-IQ-Imatrix

8B • Updated Feb 2, 2025 • 16.7k • 237

Note Fast and good model. But only 8k context that is not enough for a long RP experience.

DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS-GGUF

Text Generation • 12B • Updated Jul 28, 2025 • 500 • 38

Note Not bad model, but it writes a big chunks of text. Not good for RP, but good for stories.

mradermacher/Qwen2.5-Lumen-14B-i1-GGUF

15B • Updated Sep 22, 2024 • 251 • 8

Note Not bad for RP, but needs a proper approach.

LatitudeGames/Wayfarer-12B

Text Generation • Updated Nov 17, 2025 • 69 • • 212

Note Good at role-play and storytelling, but struggles with intimate scenes.

TheDrummer/Rivermind-12B-v1

12B • Updated Oct 31, 2025 • 10 • 47

Note Good uncensored model. A little bit funny with all these brands and slogans everywhere.

mradermacher/Ministral-Instruct-2410-8B-DPO-RP-GGUF

Text Generation • 8B • Updated Jan 21, 2025 • 156 • 2

Note Uncensored. Good context window, but sometimes it looses context. Still good for a 8b model.

Nitral-AI/Irixxed-Magcap-12B-Slerp

Text Generation • 12B • Updated Jul 12, 2025 • 31 • 30

Note Uncensored RP model with reasoning. ChatML format, but pay attention on suggested settings! May not work without a proper setup.

Phr00t/Phr00tyMix-v2-32B

Text Generation • 33B • Updated Jul 9, 2025 • 6 • 7

Note Uncensored (rarely tries to argue, just do a swipe). As a 32B model it has a better narrative and chooses words better. Likes to make a long reply (I'm testing with a 2048 tokens reply)

Phr00t/Phr00tyMix-v4-32B

Text Generation • 33B • Updated Jul 18, 2025 • 19 • 11

Note Uncensored (if tries to argue just do a swipe). As a 32B model it has a better narrative and chooses words better. LIkes to make a long reply.

mergekit-community/MN-Hekate-Limenoskopos-17B

Text Generation • 17B • Updated Apr 16, 2025 • 10 • 1

Note Uncensored. Not really better than 12B models, probably even slightly worse.

djuna/Q2.5-Veltha-14B-0.5

Text Generation • 15B • Updated Dec 22, 2024 • 113 • 11

Note Uncensored model. It have some trouble to keep consistency in small details, but swipe can give a slightly better result.

huihui-ai/Huihui-K2-Think-abliterated

Text Generation • 33B • Updated Sep 15, 2025 • 126 • 6

Note Uncensored. For my opinion this model has potential but it very slow (slower than 70b model imao), also I couldn't make it work with reasoning and reply on my settings. But what I saw is not bad, so you may try if you have a good hardware.

grimjim/Equatorium-v3-12B

Text Generation • 12B • Updated Feb 23 • 9 • 2

Note Uncensored. It feels like a successor of Magnolia-v3-12B, but with bigger chunks of text.

coder3101/gemma-4-26B-A4B-it-heretic

Image-Text-to-Text • 26B • Updated 4 days ago • 54.9k • 69

Note Uncensored. This model is quite good for role-play, but there is two issues I had with it: a) Thinking mode is still hard to setup properly in ST. In my case it mixed 'think' with 'reply'. But better use it with thinking. b) Looks like Gemma is trying to use 'soft' words instead of writing 'hard' text. In total, model is good. I'd say 3.7/5 but it doesn't fit well in 16Gb VRAM so it's quite slow.