LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

StarDust 12B V2 by Luni

 »  All LLMs  »  Luni  »  StarDust 12B V2   URL Share it on

  33   

StarDust 12B V2 is an open-source language model by Luni. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, License: apache-2.0, LLM Explorer Score: 0.22.

  Arxiv:2306.01708   Arxiv:2311.03099 Base model:finetune:gryphe/pan... Base model:gryphe/pantheon-rp-...   Chat   Conversational   Creative-writing   En   Endpoints compatible   Mistral   Model-index   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Luni/StarDust-12b-v2 

StarDust 12B V2 Benchmarks

MMLU Pro: 27.1
GPQA: 5.82
MUSR: 14.26
BBH: 34.95
IFEval: 56.29 vs 88 (so35)-36%
MATH Lvl 5: 6.87
LLME Score: 0.22169
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
StarDust 12B V2 (Luni/StarDust-12b-v2)
🌟 Advertise your project 🚀

StarDust 12B V2 Parameters and Internals

Model Type 
text-generation, roleplay, creative-writing
Use Cases 
Areas:
creative storywriting, role-play
Applications:
creative writing, roleplay scenarios
Primary Use Cases:
creative storywriting, roleplay
Limitations:
not suited for direct conversation, not suited for general purpose text generation
Considerations:
Use ChatML for better performance
Additional Notes 
The model combines various versions to enhance creative output and role-playing ability.
Supported Languages 
en (high)
Training Details 
Methodology:
DARE-TIES merge method
Input Output 
Input Format:
ChatML
Accepted Modalities:
text
Performance Tips:
Use ChatML prompting for optimal performance
LLM NameStarDust 12B V2
Repository 🤗https://huggingface.co/Luni/StarDust-12b-v2 
Base Model(s)  Mistral Nemo Bophades 12B   Magnum V2 12B   MN 12B Lyra V3   Gryphe/Pantheon-RP-1.6-12b-Nemo   nbeerbower/mistral-nemo-bophades-12B   anthracite-org/magnum-v2-12b   Sao10K/MN-12B-Lyra-v3   Gryphe/Pantheon-RP-1.6-12b-Nemo
Model Size12b
Required VRAM24.5 GB
Updated2026-04-24
MaintainerLuni
Model Typemistral
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.44.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to StarDust 12B V2

Best Alternatives
Context / RAM
Downloads
Likes
Celestial Queen 12B1000K / 24.5 GB37811
MN 12B Mag Mell R11000K / 24.5 GB9462237
MN 12B LucidFaun RP RU1000K / 24.5 GB1855
...s PersonalityEngine V1.1.0 12B1000K / 24.5 GB65145
Captain Eris BMO Violent 12B1000K / 24.5 GB3052
Dans SakuraKaze V1.0.0 12B1000K / 24.5 GB4020
...n Eris BMO Violent GRPO V0.4201000K / 24.5 GB923
Celestial Queen 12B Heretic1000K / 24.5 GB144
DoublePotato Mistral Nemo 13B1000K / 26.8 GB111
Mistral Nemo Kartoffel 12B1000K / 24.5 GB156
Note: green Score (e.g. "73.2") means that the model is better than Luni/StarDust-12b-v2.

Rank the StarDust 12B V2 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53570 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer