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

FluffyKaeloky Luminum V0.1 123B EXL2 2.7bpw H6 by BigHuggyD

 »  All LLMs  »  BigHuggyD  »  FluffyKaeloky Luminum V0.1 123B EXL2 2.7bpw H6   URL Share it on

  4   

FluffyKaeloky Luminum V0.1 123B EXL2 2.7bpw H6 is an open-source language model by BigHuggyD. Features: 123b LLM, VRAM: 42.3GB, Context: 128K, Quantized, LLM Explorer Score: 0.15.

  Conversational   Endpoints compatible   Exl2   Merge   Mergekit   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/BigHuggyD/FluffyKaeloky_Luminum-v0.1-123B_exl2_2.7bpw_h6 

FluffyKaeloky Luminum V0.1 123B EXL2 2.7bpw H6 Benchmarks

LLME Score: 0.14513
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
FluffyKaeloky Luminum V0.1 123B EXL2 2.7bpw H6 (BigHuggyD/FluffyKaeloky_Luminum-v0.1-123B_exl2_2.7bpw_h6)
🌟 Advertise your project 🚀

FluffyKaeloky Luminum V0.1 123B EXL2 2.7bpw H6 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Applications:
daily text generation tasks
Primary Use Cases:
long context generation, creative descriptions
Limitations:
tends to generate long responses
Considerations:
Use specific settings to optimize performance.
Additional Notes 
Merged using Mistral template.
Training Details 
Methodology:
della_linear merge method
Input Output 
Input Format:
~~[INST] {input} [/INST] {output}~~
Accepted Modalities:
text
Performance Tips:
Use settings: Minp: 0.08, Rep penalty: 1.03, Rep penalty range: 4096, Smoothing factor: 0.23, No Repeat NGram Size: 2.
LLM NameFluffyKaeloky Luminum V0.1 123B EXL2 2.7bpw H6
Repository 🤗https://huggingface.co/BigHuggyD/FluffyKaeloky_Luminum-v0.1-123B_exl2_2.7bpw_h6 
Model Size123b
Required VRAM42.3 GB
Updated2026-06-26
MaintainerBigHuggyD
Model Typemistral
Model Files  8.6 GB: 1-of-5   8.6 GB: 2-of-5   8.5 GB: 3-of-5   8.6 GB: 4-of-5   8.0 GB: 5-of-5
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.44.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to FluffyKaeloky Luminum V0.1 123B EXL2 2.7bpw H6

Best Alternatives
Context / RAM
Downloads
Likes
Soar Mistral 123B128K / 217.2 GB81
Behemoth X R1 123B128K / 216.7 GB62
Behemoth X 123B V2.1128K / 222 GB187
Behemoth R1 123B V2128K / 226.4 GB13429
Behemoth X 123B V2128K / 217.2 GB5431
Behemoth ReduX 123B V1128K / 217.2 GB2614
ML2 123B Magnum Diamond128K / 212.4 GB612
Monstral 123B V2128K / 245.4 GB81847
Behemoth 123B V2.1128K / 226.4 GB65718
Behemoth 123B V1128K / 221.6 GB112944
Note: green Score (e.g. "73.2") means that the model is better than BigHuggyD/FluffyKaeloky_Luminum-v0.1-123B_exl2_2.7bpw_h6.

Rank the FluffyKaeloky Luminum V0.1 123B EXL2 2.7bpw H6 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? 54931 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