GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
waddie
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
waddie
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This model used 10k discord conversations.
Unlike standard AI assistants that are helpful and formal, this model adopts a "random guy" persona. It was trained on curated conversation pairs from an AI Leaks community to capture a casual, lowercase-heavy, and slightly secretive "insider" vibe.
This model is intended for Discord bots or roleplay scenarios where a "human-like" interaction is preferred over a robotic assistant.
To get the best "human" feel, use all lowercase and skip formal punctuation.
Recommended Format (ChatML):
text
<|im_start|>useryo did you see the new internal model?<|im_end|><|im_start|>assistant