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

Qwen2 72B Instruct Mix Calibration 4B EXL2 by Orion-zhen

 »  All LLMs  »  Orion-zhen  »  Qwen2 72B Instruct Mix Calibration 4B EXL2   URL Share it on

  7   

Qwen2 72B Instruct Mix Calibration 4B EXL2 is an open-source language model by Orion-zhen. Features: 72b LLM, VRAM: 38.8GB, Context: 32K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.14.

  Arxiv:2309.00071   4-bit   Chat   Conversational   En   Endpoints compatible   Exl2   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Orion-zhen/Qwen2-72B-Instruct-mix-calibration-4b-exl2 

Qwen2 72B Instruct Mix Calibration 4B EXL2 Benchmarks

LLME Score: 0.1379
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 72B Instruct Mix Calibration 4B EXL2 (Orion-zhen/Qwen2-72B-Instruct-mix-calibration-4b-exl2)
🌟 Advertise your project 🚀

Qwen2 72B Instruct Mix Calibration 4B EXL2 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Supported Languages 
en (High)
Training Details 
Methodology:
Pretrained with a large amount of data, and post-trained with both supervised finetuning and direct preference optimization.
Context Length:
131072
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc.
Input Output 
Accepted Modalities:
text
Performance Tips:
To handle extensive inputs exceeding 32,768 tokens, utilize YARN for enhancing model length extrapolation ensuring optimal performance on lengthy texts.
LLM NameQwen2 72B Instruct Mix Calibration 4B EXL2
Repository 🤗https://huggingface.co/Orion-zhen/Qwen2-72B-Instruct-mix-calibration-4b-exl2 
Model Size72b
Required VRAM38.8 GB
Updated2026-04-17
MaintainerOrion-zhen
Model Typeqwen2
Instruction-BasedYes
Model Files  8.5 GB: 1-of-5   8.6 GB: 2-of-5   8.5 GB: 3-of-5   8.5 GB: 4-of-5   4.7 GB: 5-of-5
Supported Languagesen
Quantization Typeexl2
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.40.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2 72B Instruct Mix Calibration 4B EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct 2.0bpw H Novel EXL2125K / 23 GB51
Qwen2 72B Instruct 4bit32K / 40.9 GB212
ECE ILAB Q132K / 77.8 GB670
Qwen2.5 72B Instruct Bnb 4bit32K / 41.4 GB56668
Qwen2.5 72B Instruct 4bit32K / 40.9 GB16485
Athene V2 Chat 4.65bpw H6 EXL232K / 44.3 GB86
Qwen2.5 72B Instruct 8bit32K / 77.1 GB2943
Qwen2 72B Instruct Bpw5.5 EXL232K / 51.8 GB31
Qwen2 72B Instruct Bnb 4bit32K / 41.2 GB417
Qwen2 72B Instruct Bpw4 EXL232K / 38.7 GB80
Note: green Score (e.g. "73.2") means that the model is better than Orion-zhen/Qwen2-72B-Instruct-mix-calibration-4b-exl2.

Rank the Qwen2 72B Instruct Mix Calibration 4B EXL2 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? 53151 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