SufficientPrune3897/Llama-3.3-8B-Character-Creator-V2-GGUF

Llama-3.3-8B-Character-Creator-V2 - GGUF Quants

GGUF quantizations of SufficientPrune3897/Llama-3.3-8B-Character-Creator-V2.

This is a model made to create characters that can be used in Sillytavern, cai, jai and other such roleplay scenarios. The resulting characters should be about ~2k tokens and follow a prebaked structure.

Versions:

• 8B llama 3.3 based (this one) and GGUFs
• 12B gemma 3 based and GGUFs
• 24B mistral small 3.2 based and GGUFs
• (maybe) 27B gemma 3 based and GGUFs

How to use it:

• Simply tell the model what you want your character to be.
• It should know many popular franchises, the bigger the model, the more it knows.
• Fully uncensored.
• Asking for a different structure than the one the model uses might significantly reduce result quality.
• While follow up questions are supported, you will often get better results adjusting your original prompt.
• Supports asking for: prompts for pictures of the char, asking for changes and making an intro.

Changes from V1

• No longer supports Groups and scenarios
• Characters should be much better
• It actually follows a structure and doesnt start making shit up after ~1k tokens

Available Quants

Filename	Quant	Size	Description
Llama-3.3-8B-Character-Creator-V2-Q8_0.gguf	Q8_0	8.0GB	Maximum quality, near-lossless
Llama-3.3-8B-Character-Creator-V2-Q5_K_M.gguf	Q5_K_M	5.4GB	High quality, recommended
Llama-3.3-8B-Character-Creator-V2-Q4_K_M.gguf	Q4_K_M	4.6GB	Good quality, good balance
Llama-3.3-8B-Character-Creator-V2-IQ4_NL.gguf	IQ4_NL	4.4GB	Good quality, slightly smaller than Q4_K_M
Llama-3.3-8B-Character-Creator-V2-IQ3_M.gguf	IQ3_M	3.6GB	Smaller, some quality loss

V3 and beyond:

The next version will either reintroduce scenarios, groups or feature reasoning. Probably both. Perhaps even lorebooks, although I'm still unsure how to execute on that... After that I will probably make my own real roleplay finetune or something.

If anybody wants support of their native language just ask me and tell me what model does the best for that.

I am very much open for feedback. A single comment can easily change how I will do my next version.

---

• Developed by: SufficientPrune3897
• License: apache-2.0
• Finetuned from model: YanLabs/Llama-3.3-8B-Instruct-MPOA
• Quantized with: llama.cpp

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.