Qwen2 7B Instruct MLX by Qwen

 ยป  All LLMs  ยป  Qwen  ยป  Qwen2 7B Instruct MLX   URL Share it on

  Chat   Conversational   En   Instruct   Qwen2   Region:us   Safetensors

Qwen2 7B Instruct MLX Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 7B Instruct MLX (Qwen/Qwen2-7B-Instruct-MLX)

Qwen2 7B Instruct MLX Parameters and Internals

Model Type 
text generation, multilingual
Additional Notes 
This is the MLX quantized model of Qwen2-0.5B-Instruct.
Supported Languages 
en (default)
Training Details 
Methodology:
Pretraining with a large amount of data; post-training with supervised finetuning and direct preference optimization.
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, improved tokenizer.
LLM NameQwen2 7B Instruct MLX
Repository ๐Ÿค—https://huggingface.co/Qwen/Qwen2-7B-Instruct-MLX 
Model Size7b
Required VRAM4.3 GB
Updated2025-01-24
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  4.3 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2 7B Instruct MLX

Best Alternatives
Context / RAM
Downloads
Likes
Rombos LLM V2.5 Qwen 7B128K / 15.2 GB66215
Qwen2 7B Instruct V0.1128K / 15.2 GB409681
Gte Qwen2 7B Instruct128K / 30.5 GB43899248
Rombo LLM V2.5 Qwen 7B128K / 15.2 GB321
Cybertron V4 Qw7B UNAMGS128K / 15.2 GB918
Model 3128K / 15.2 GB420
Qwen2 7B Instruct V0.8128K / 15.2 GB409903
Cybertron V4 Qw7B MGS128K / 15.2 GB6912
...eCyberMix Qwen 2.5 7B Instruct128K / 15.2 GB172
Tsunami 0.5x 7B Instruct128K / 15.2 GB1341
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2-7B-Instruct-MLX.

Rank the Qwen2 7B Instruct MLX 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? 41817 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227