Qwen2 7B 8bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Qwen2 7B 8bit   URL Share it on

  8bit   Conversational   En   License:apache-2.0   Mlx   Pretrained   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Rank the Qwen2 7B 8bit 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  
Qwen2 7B 8bit (mlx-community/Qwen2-7B-8bit)

Best Alternatives to Qwen2 7B 8bit

Best Alternatives
HF Rank
Qwen2 7B 4bit128K / 4.3 GB80
...lphin 2.9.2 Qwen2 7B Bpw4 EXL2128K / 4.8 GB60
Qwen2 7B Bnb 4bit128K / 5.5 GB99472
Qwen2 7B Alpacha Merged 4bit128K / 5.6 GB150
PiSSA Qwen2 7B 4bit R128 5iter128K / 5.9 GB940
...lphin 2.9.2 Qwen2 7B Bpw6 EXL2128K / 6.4 GB21
Qwen2 7B Matter 0.1 Slim A128K / 15.2 GB52
Josiev4o 7B Stage1 V0.1128K / 15.2 GB01
Qwen V2 7B Merged 16bit SA128K / 15.2 GB380
...odeQwen1.5 7B Chat EXL2 8.0bpw64K / 7.5 GB54

Qwen2 7B 8bit Parameters and Internals

LLM NameQwen2 7B 8bit
RepositoryOpen on ๐Ÿค— 
Model Size7b
Required VRAM8.1 GB
Model Typeqwen2
Model Files  5.3 GB: 1-of-2   2.8 GB: 2-of-2
Supported Languagesen
Quantization Type8bit
Model ArchitectureQwen2ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.37.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 36243 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801