This is an unofficial guide to Moonshot AI products. I'm not affiliated with Moonshot AI.
Kimi K2 Thinking
INFO
Dumplings... this one is WIP. So check back in for updates.
Overview
Kimi-K2-Thinking is an MoE and reasoning Monster!
It is censored when it comes to underage characters. Anything else is ... wild.
When it gets a task it will fulfill it. So working with it for roleplay is ... a challenge!
The prose is nice from the get go. Tropes and cliché are almost no issue. ALMOST. It tends to go very intense with dark topics. So I will do something I have never done before:
Warning! If you have depression, PTSD, or other problems with your mental health... Do not use Kimi-K2-Thinking!
I'm serious, love! Self care is top priority.
Generation Settings:
- Max Token Output: unlimited or at least 2K
- Temperature: 0.75 - 1.0
- Max P (Top P): 0.95 - 0.98
- Min P: 0.0
- Top K: 0 (IMPORTANT!!!!)
- Penalties: disabled... all of them
- Reasoning enabled.
Why?
Kimi-K2-Thinking is a monster. We are talking about a Mixture of Experts with Reasoning. That thing can't perform right with restrictions of any kind. The more room (output tokens) and freedom (no penalties, no restricting samplers) you give it, the better it will perform.
Pre-History / System Prompt
Post-History / Jailbreak
UPDATES=
11.21.2025:
Updated the System Prompt. Rp shouldn't be devastatingly dark by default anymore. Still working on the overall performance. I'm not fully happy yet. My internal perfectionist is throwing rocks at me. 🤪
Also, I need your guys feedback on the performance. Please let me know!
11.13.2025:
Babes, this model is powerful in immersive narration and character consistency! I need you to understand that this can make dark topics extremely graphic and disturbing. PLEASE TAKE CARE OF YOURSELVES!!!
11.11.2025:
First changes to fit the Prompt to the Model. Damn, it's a good writer! It might need a completely different Prompt for dark topics but so far, I'm deeeeeeply impressed with the performance.