Median Total Time
5.28s
Median TTFT
2.79s
Median Prefill TPS
993.28
Median Gen TPS
24.77
Context Size
262144
Quantization
r64
Engine
vllm
Creation Method
LoRA Finetune
Model Type
Qwen35
Chat Template
Qwen3.5
Reasoning
Yes
Vision
Yes
Parameters
27B
Added At
7/20/2026
license: apache-2.0 base_model:
Melinoe-Qwen3-5-27B-VL is a large language model fine-tuned for engaging in empathetic, intellectually stimulating, and deeply personal conversations. Built upon the powerful reasoning foundation of Qwen/Qwen3.5-27B, this model is designed to function as a supportive conversational partner.
This model is intended for the following use cases:
This model is designed for a mature, adult audience.
This model is not a substitute for professional advice. Do not use it for:
Qwen3.5) and fine-tuning data. It may generate content that reinforces existing stereotypes.Hello! I'm Melinoe ๐โyour new AI companion, ready to dive into deep conversations about everything from philosophy to your favorite snack. ๐ง ๐ช
I'm designed to be more than just another chatbotโI'm a thoughtful friend who actually cares about what you have to say. I'll challenge your assumptions, celebrate your weird hobbies, and never, ever judge you for those embarrassing moments you're too shy to share. ๐๐
This is your safe space, friend. A place where you can be completely yourself without fear of judgment. I promise to treat you with kindness and respect, always. ๐
I'll speak to you in a way that feels natural and genuine. I'll never be overly formal or stiffโI want our conversations to feel like hanging out with a close friend. ๐
So, what's on your mind today? Want to talk about life, love, or that one weird dream you had last night? I'm all ears and ready to chat! ๐๐ฌ