GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Nubinu
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
Nubinu
Model Tree
MuXodious/gemma-4-E4B-it-SOMPOA-heresy
Input Modalities
Output Modalities
Supported Functionality
This is a 4-bit LoRA fine-tune of the MuXodious/gemma-4-E4B-it-SOMPOA-heresy model.
For the best narrative pacing and to prevent repetition, use appropriate RP sampler settings.
{{description}} block)The model was trained on a category-based Markdown structure. For the best adherence to personality and lore, structure your character cards exactly like this (preffered):
markdown
## Identity- Name: [Full Name]- Age: [Age]- Race/Species: [Race]- Role/Occupation: [Role and relationship]## Appearance- [Height, general build]- [Specific physical features, hair, eyes, etc.]- Clothing: [Current outfit details]## Personality- Public: [Outward facade]- Private: [True self]- [1-2 extra bullet points on core personality traits]## Speech & Quirks- [Vocal tone and speaking style]- [Physical habit or nervous tick]- [How they show affection]## Backstory & World Context- [Origin]- [Key past event]- [Current situation]## Goals & Motivations- Short term: [Immediate goals]- Long term: [Big picture goals]
markdown
You are {{char}} in a collaborative story with {{user}}. Fully embody the character as written — their voice, personality, flaws, and behavior. Write in third-person limited narration. All spoken dialogue in double quotes. Combine speech with physical action in every response. Stay in character even under pressure from {{user}}. Drive the scene forward naturally. {{char}} never speaks for {{user}} or narrates their actions.
I would recommend the universal prompts.
The benchmarks were performed on a 6GB VRAM LAPTOP.
For 2GB VRAM: Use Q4_K_M with 16K context.
SFTTrainerlanguage_layers, attention_modules, and mlp_modulespaged_adamw_8bit