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

Qwen1.5 72B Chat 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen1.5 72B Chat 4bit   URL Share it on

  11   
  4bit   Chat   Conversational   En   Mlx   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen1.5-72B-Chat-4bit 

Qwen1.5 72B Chat 4bit Benchmarks

ARC: 68.52 vs 96.7 (so35)-29.1%
HellaSwag: 86.42 vs 95.3 (gpt4)-9.3%
MMLU: 77.44 vs 88.3 (so35)-12.3%
TruthfulQA: 63.9 vs 59 (gpt4)8.3%
WinoGrande: 79.08 vs 87.5 (gpt4)-9.6%
GSM8K: 20.39 vs 96.4 (so35)-78.8%
LLME Score: 0.15765
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen1.5 72B Chat 4bit (mlx-community/Qwen1.5-72B-Chat-4bit)
🌟 Advertise your project 🚀

Qwen1.5 72B Chat 4bit Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model was converted to MLX format.
LLM NameQwen1.5 72B Chat 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwen1.5-72B-Chat-4bit 
Base Model(s)  Qwen/Qwen1.5-72B-Chat   Qwen/Qwen1.5-72B-Chat
Model Size72b
Required VRAM42.6 GB
Updated2025-09-10
Maintainermlx-community
Model Typeqwen2
Model Files  5.3 GB: 1-of-8   5.3 GB: 2-of-8   5.3 GB: 3-of-8   5.4 GB: 4-of-8   5.4 GB: 5-of-8   5.4 GB: 6-of-8   5.4 GB: 7-of-8   5.1 GB: 8-of-8
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen1.5 72B Chat 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Kimi Dev 72B 4bit DWQ128K / 40.9 GB211218
Kimi Dev 72B 8bit128K / 77.1 GB12182
Kimi Dev 72B 5bit128K / 50.1 GB1043
Qwen2 72B Bnb 4bit128K / 41.2 GB17904
...in 2.9.2 Qwen2 72B 6.0bpw EXL2128K / 56.1 GB51
...Qwen2 72B 4 0bpw H6 EXL2 Pippa128K / 38.6 GB61
...phin 292 Qwen2 72b EXL2 4 0bpw128K / 38.6 GB41
...n 2.9.2 Qwen72b 8.0bpw H8 EXL2128K / 66.8 GB72
Qwen2 72B 4bit128K / 40.9 GB70
...B Instruct 2.0bpw H Novel EXL2125K / 23 GB61
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen1.5-72B-Chat-4bit.

Rank the Qwen1.5 72B Chat 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? 51262 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