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

Aetheria L2 70B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Aetheria L2 70B AWQ   URL Share it on

  8   
  4-bit   Autotrain compatible   Awq Base model:quantized:royallab/... Base model:royallab/aetheria-l...   En   Llama   Llama 2   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/Aetheria-L2-70B-AWQ 

Aetheria L2 70B AWQ Benchmarks

LLME Score: 0.12274
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Aetheria L2 70B AWQ (TheBloke/Aetheria-L2-70B-AWQ)
🌟 Advertise your project 🚀

Aetheria L2 70B AWQ Parameters and Internals

Model Type 
llama, text-generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Collaborative storytelling, Roleplaying
Primary Use Cases:
Roleplaying chat, Story generation
Limitations:
Bias similar to niche roleplaying forums, Not for factual information or advice
Additional Notes 
Uses length modifier for controlling message output.
Supported Languages 
en (English)
Training Details 
Methodology:
Merge of multiple models including Euryale v1.3, Tulu v2, GOAT Storytelling, and LimaRP v3 for collaborative storytelling and roleplay.
Input Output 
Input Format:
Alpaca instruction format of LimaRP v3
Output Format:
Character responses in roleplaying chat with medium-length messages
LLM NameAetheria L2 70B AWQ
Repository 🤗https://huggingface.co/TheBloke/Aetheria-L2-70B-AWQ 
Model NameAetheria L2 70B
Model CreatorThe Royal Lab
Base Model(s)  Aetheria L2 70B   royallab/Aetheria-L2-70B
Model Size70b
Required VRAM36.6 GB
Updated2025-09-20
MaintainerTheBloke
Model Typellama
Model Files  9.9 GB: 1-of-4   9.9 GB: 2-of-4   9.9 GB: 3-of-4   6.9 GB: 4-of-4
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Aetheria L2 70B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...0B Instruct Gradient 1048K AWQ1024K / 39.9 GB121
...70B Instruct Gradient 262K AWQ256K / 39.9 GB60
Llama 3.3 70B Instruct AWQ128K / 39.9 GB3649906
Llama 3.3 70B Instruct AWQ128K / 39.9 GB15931735
...lama 3.3 70B Instruct AWQ INT4128K / 39.9 GB3142825
... SauerkrautLM 70B Instruct AWQ128K / 39.9 GB795
MultiVerse 70B AWQ32K / 41.3 GB72
Opus V1.2 70B AWQ32K / 36.7 GB81
QuartetAnemoi 70B T0.0001 AWQ31K / 36.7 GB61
Senku 70B AWQ 4bit GEMM31K / 36.7 GB61
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Aetheria-L2-70B-AWQ.

Rank the Aetheria L2 70B AWQ 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? 51483 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.
Release v20241124
  Support LLM Explorer