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

Ao Karasu 72B AWQ 4bit by lightblue

 »  All LLMs  »  lightblue  »  Ao Karasu 72B AWQ 4bit   URL Share it on

  5   

Ao Karasu 72B AWQ 4bit is an open-source language model by lightblue. Features: 72b LLM, VRAM: 41.3GB, Context: 32K, Quantized, Merged, LLM Explorer Score: 0.12.

  Merged Model   4-bit   4bit   Awq   Conversational   Endpoints compatible   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/lightblue/ao-karasu-72B-AWQ-4bit 

Ao Karasu 72B AWQ 4bit Benchmarks

LLME Score: 0.12369
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ao Karasu 72B AWQ 4bit (lightblue/ao-karasu-72B-AWQ-4bit)
🌟 Advertise your project 🚀

Ao Karasu 72B AWQ 4bit Parameters and Internals

Model Type 
text generation, chatbot
Use Cases 
Areas:
AI assistance
Applications:
chat-based applications
Primary Use Cases:
Conversation with users in various domains
Additional Notes 
The model was trained with a focus on Japanese language proficiency.
Supported Languages 
Japanese (proficient)
Training Details 
Data Sources:
Wikipedia-based QA, technical blogs, Japanese QA site answers, LLM generated prompts and responses, news articles
Data Volume:
1.1 billion characters
Training Time:
~1 day
Hardware Used:
A100 (80GB) GPU
Input Output 
Input Format:
Prompt format using chat template.
Accepted Modalities:
text
Output Format:
Text
LLM NameAo Karasu 72B AWQ 4bit
Repository 🤗https://huggingface.co/lightblue/ao-karasu-72B-AWQ-4bit 
Merged ModelYes
Model Size72b
Required VRAM41.3 GB
Updated2026-04-07
Maintainerlightblue
Model Typeqwen2
Model Files  5.0 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   5.0 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   5.0 GB: 7-of-9   3.8 GB: 8-of-9   2.5 GB: 9-of-9
AWQ QuantizationYes
Quantization Typeawq|4bit
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.39.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Ao Karasu 72B AWQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Tess V2.5.2 Qwen2 72B AWQ128K / 41.6 GB50
Qwen1.5 72B Chat AWQ32K / 41.3 GB31526
Qwen2.5 72B Instruct AWQ32K / 41.6 GB18143072
Athene V2 Chat AWQ32K / 41.6 GB54
Qwen2 72B Instruct AWQ32K / 41.6 GB42641
Qwen2 72B Instruct AWQ GEMM32K / 41.6 GB60
Qwen1.5 72B AWQ32K / 41.3 GB11
Typhoon V1.5 72B Instruct AWQ32K / 41.3 GB73
Typhoon V1.5 72B Instruct AWQ32K / 41.3 GB53
Liberated Qwen1.5 72B AWQ32K / 41.3 GB81
Note: green Score (e.g. "73.2") means that the model is better than lightblue/ao-karasu-72B-AWQ-4bit.

Rank the Ao Karasu 72B AWQ 4bit 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