Hunyuan A52B Instruct 3bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Hunyuan A52B Instruct 3bit   URL Share it on

  3-bit   3bit   Autotrain compatible Base model:quantized:tencent-c... Base model:tencent-community/h...   Conversational   Custom code   En   Hunyuan   Instruct   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Hunyuan A52B Instruct 3bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hunyuan A52B Instruct 3bit (mlx-community/Hunyuan-A52B-Instruct-3bit)

Hunyuan A52B Instruct 3bit Parameters and Internals

LLM NameHunyuan A52B Instruct 3bit
Repository ๐Ÿค—https://huggingface.co/mlx-community/Hunyuan-A52B-Instruct-3bit 
Base Model(s)  Hunyuan A52B Instruct   tencent-community/Hunyuan-A52B-Instruct
Model Size60.7b
Required VRAM193.8 GB
Updated2024-12-26
Maintainermlx-community
Model Typehunyuan
Instruction-BasedYes
Model Files  5.3 GB: 1-of-39   5.4 GB: 2-of-39   5.1 GB: 3-of-39   4.9 GB: 4-of-39   5.1 GB: 5-of-39   5.1 GB: 6-of-39   4.9 GB: 7-of-39   5.1 GB: 8-of-39   5.1 GB: 9-of-39   4.9 GB: 10-of-39   5.1 GB: 11-of-39   5.1 GB: 12-of-39   4.9 GB: 13-of-39   5.1 GB: 14-of-39   5.1 GB: 15-of-39   4.9 GB: 16-of-39   5.1 GB: 17-of-39   5.1 GB: 18-of-39   4.9 GB: 19-of-39   5.1 GB: 20-of-39   5.1 GB: 21-of-39   4.9 GB: 22-of-39   5.1 GB: 23-of-39   5.1 GB: 24-of-39   4.9 GB: 25-of-39   5.1 GB: 26-of-39   5.1 GB: 27-of-39   4.9 GB: 28-of-39   5.1 GB: 29-of-39   5.1 GB: 30-of-39   4.9 GB: 31-of-39   5.1 GB: 32-of-39   5.1 GB: 33-of-39   4.9 GB: 34-of-39   5.1 GB: 35-of-39   5.1 GB: 36-of-39   4.9 GB: 37-of-39   5.1 GB: 38-of-39   1.9 GB: 39-of-39
Supported Languagesen
Quantization Type3bit
Model ArchitectureHunYuanForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Vocabulary Size129024
Torch Data Typebfloat16

Rank the Hunyuan A52B Instruct 3bit Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40248 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217