Roleplay GGUF models
7765 GGUF models: models tuned for roleplay and character chat. Sizes run from 3M to 426B parameters. The longest trained context is 4192K tokens.
About Roleplay GGUF models
7,765 GGUF models are filed under Roleplay: models tuned for roleplay and character chat. The most downloaded are Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP, Qwen3.8 27B TURBO Fable Cold Fusion 735 882 Heretic Uncensored NEO CODER MAX MTP and Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced. Parameter counts run from 3M to 426B, and the longest trained context window is 4192K tokens.
Roleplay models are tuned for character chat and long conversations, so context length and memory for the KV cache matter. The families you will see most are Qwen (1230), Llama (745) and Gemma (436).
Frequently asked questions
What are Roleplay GGUF models?
Models tuned for roleplay and character chat. There are 7,765 of them on this site.
Which Roleplay GGUF model should I start with?
The most downloaded is Qwen3.5 9B The Defiant Fable Uncensored Heretic NEO IMATRIX MAX MTP. Choose the size that fits your GPU, then a Q4_K_M quant unless you have memory to spare.