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

Aurora Nights 103B V1.0 GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Aurora Nights 103B V1.0 GPTQ   URL Share it on

  3   

Aurora Nights 103B V1.0 GPTQ is an open-source language model by TheBloke. Features: 103b LLM, VRAM: 52.5GB, Context: 4K, License: llama2, Quantized, LLM Explorer Score: 0.11.

  Arxiv:2307.11760   4-bit Base model:quantized:sophosymp... Base model:sophosympatheia/aur...   En   Gptq   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Aurora-Nights-103B-v1.0-GPTQ 

Aurora Nights 103B V1.0 GPTQ Benchmarks

LLME Score: 0.11137
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Aurora Nights 103B V1.0 GPTQ (TheBloke/Aurora-Nights-103B-v1.0-GPTQ)
🌟 Advertise your project 🚀

Aurora Nights 103B V1.0 GPTQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
roleplaying, storytelling
Primary Use Cases:
creative writing, instruction following
Limitations:
Limited performance on tasks outside creative writing and roleplaying
Considerations:
User responsibility for use.
Additional Notes 
Features 120 layers and is a frankenmerge of its predecessor, improving on storytelling.
Supported Languages 
en (proficient)
Training Details 
Methodology:
Frankenmerge of Aurora-Nights-70B-v1.0 with itself
Context Length:
8192
Model Architecture:
120 layers, float16 dtype
Input Output 
Input Format:
{system_message} <|user|> {prompt} <|assistant|>
Accepted Modalities:
text
LLM NameAurora Nights 103B V1.0 GPTQ
Repository 🤗https://huggingface.co/TheBloke/Aurora-Nights-103B-v1.0-GPTQ 
Model NameAurora Nights 103B v1.0
Model CreatorSophosympatheia
Base Model(s)  sophosympatheia/Aurora-Nights-103B-v1.0   sophosympatheia/Aurora-Nights-103B-v1.0
Model Size103b
Required VRAM52.5 GB
Updated2026-04-01
MaintainerTheBloke
Model Typellama
Model Files  49.0 GB: 1-of-2   3.5 GB: 2-of-2
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Aurora Nights 103B V1.0 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Rogue Rose 103B V0.2 GPTQ4K / 52.5 GB91
Solus 103B L2 GPTQ4K / 52.6 GB71
Lila 103B L2 GPTQ4K / 52.6 GB61
... Dark Miqu 103B 5.0bpw H8 EXL231K / 65.1 GB50
... Miqu 103B V1.5 3.5bpw H6 EXL231K / 45.6 GB51
...qu 103B V1.5 EXL2 5.0bpw Rpcal31K / 64.9 GB41
...qu 103B V1.5 EXL2 4.0bpw Rpcal31K / 52.1 GB91
...qu 103B V1.5 EXL2 3.0bpw Rpcal31K / 39.3 GB21
...ght Miqu 103B V1.0 EXL2 4.5bpw31K / 58.7 GB51
...ght Miqu 103B V1.0 EXL2 4.0bpw31K / 52.2 GB21
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Aurora-Nights-103B-v1.0-GPTQ.

Rank the Aurora Nights 103B V1.0 GPTQ 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? 52721 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