Sukino/SillyTavern-Settings-and-Presets

Chatbots	Settings	Guides	Index

Sukino's SillyTavern Settings and Presets

Go to the Files and versions tab to view and download my settings.

What I'm Using

Software

• KoboldCPP: https://github.com/LostRuins/koboldcpp — My backend of choice for running models locally.
• SillyTavern: https://github.com/SillyTavern/SillyTavern — My frontend of choice, the bridge between you and the AI model. Load your characters in it, connect to KoboldCPP and start chatting.
• MikuPad: https://lmg-anon.github.io/mikupad/mikupad.html — Want to understand how LLMs work in a minute? Use this to talk directly to the model without characters and system prompts in the way. I use it all the time to test how the model talks and responds to prompts on its own, and what it can or can't do.
• ComfyUI: https://github.com/comfyanonymous/ComfyUI / https://github.com/ltdrdata/ComfyUI-Manager — My image generation software of choice. Node based, not really beginner friendly, but it's pretty powerful, you have control over every single generation step.

Text Generation Models

These days I just really use bigger models via API. With Deepseek and GLM, it has become much more accessible, and it's hard to go back to local, smaller models. Still, these are the ones I used the most:

• Mistral Small Instruct 2409: https://huggingface.co/mistralai/Mistral-Small-Instruct-2409 — Are these Small models really 20B? They feel a lot smarter than they should. I used this model a lot, but the prose is pretty bland, and it needs a well thought-out prompt to RP well. I prefer blandness to sacrificing smartness for a finetune.
  • Magistral Small 2509: https://huggingface.co/mistralai/Magistral-Small-2509 — The more up-to-date version of the same model.
• Gemma 2 9B IT: https://huggingface.co/google/gemma-2-9b-it — It's an impressive model, has a fantastic prose for such a small size, feels better than even 12B models. But it's pretty censored by default, you'll need to jailbreak it for not-so-wholesome RPs. And don't go beyond 12K context, the model will break.
• Cydonia-v1.2-Magnum-v4-22B: https://huggingface.co/knifeayumu/Cydonia-v1.2-Magnum-v4-22B — Magnum V2 and V3 were great models, while V4 was kind of a miss. But for some reason, merging it with Cydonia made Cydonia even better? Go figure.
• MN 12B Mag Mell R1: https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1 — Best 12B model for RP to date, imo, as smart as a 12B Mistral based model can be.
• Wayfarer 12B: https://huggingface.co/LatitudeGames/Wayfarer-12B — Curious model, not the best for general RP, but shines if you like the AI Dungeon format, it was trained for that.
  • Wayfarer 2 12B: https://huggingface.co/LatitudeGames/Wayfarer-2-12B — The more up-to-date version of the same model.

Image Generation Models

• NoobAI-XL V-Pred: https://huggingface.co/Laxhar — I used to use merges for a long time, but these days, I just use the base model and apply LORAs to change the style when I want. V-Pred models are a bit harder to work with, and have way less content for them, but they follow prompts better and have significantly better contrast and blacks. It's really cool to experiment with lighting when using them.
• ΣΙΗ: https://civitai.com/models/1217645/sih — What the hell, how do you read that? I just call it sigma. Another NoobAI merge. Still testing it, but I feel like it's a big improvement over CyberFix, it's taken its place for now.
• NoobAICyberFix: https://civitai.com/models/913998/noobaicyberfix — NoobAI is one of the latest efforts for anime-style, could easily replace Pony as the standard. This CyberFix makes it easier to work with.