Qwen2 57B A14B Instruct 4bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Qwen2 57B A14B Instruct 4bit   URL Share it on

  4bit   Chat   Conversational   En   Instruct   Mlx   Quantized   Qwen2 moe   Region:us   Safetensors   Sharded   Tensorflow

Qwen2 57B A14B Instruct 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen2 57B A14B Instruct 4bit Parameters and Internals

LLM NameQwen2 57B A14B Instruct 4bit
Repository ๐Ÿค—https://huggingface.co/mlx-community/Qwen2-57B-A14B-Instruct-4bit 
Base Model(s)  Qwen2 57B A14B Instruct   Qwen/Qwen2-57B-A14B-Instruct
Model Size57b
Required VRAM32.3 GB
Updated2024-09-07
Maintainermlx-community
Model Typeqwen2_moe
Instruction-BasedYes
Model Files  5.2 GB: 1-of-7   5.3 GB: 2-of-7   5.2 GB: 3-of-7   5.3 GB: 4-of-7   5.3 GB: 5-of-7   5.2 GB: 6-of-7   0.8 GB: 7-of-7
Supported Languagesen
Quantization Type4bit
Model ArchitectureQwen2MoeForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.40.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace
Qwen2 57B A14B Instruct 4bit (mlx-community/Qwen2-57B-A14B-Instruct-4bit)

Best Alternatives to Qwen2 57B A14B Instruct 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2 57B A14B Instruct 8bit32K / 61.1 GB251
Qwen2 57B A14B Instruct32K / 115.2 GB771573
...n2 57B A14B Instruct GPTQ Int432K / 31.6 GB62523
...7B A14B Instruct GPTQ Int4 MLX32K / 32.3 GB471
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen2-57B-A14B-Instruct-4bit.

Rank the Qwen2 57B A14B Instruct 4bit 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? 35693 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803