Qwen3 4B 4bit DWQ by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Qwen3 4B 4bit DWQ   URL Share it on

  4-bit   4bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-4b   Conversational   Mlx   Quantized   Qwen3   Region:us   Safetensors

Qwen3 4B 4bit DWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 4B 4bit DWQ (mlx-community/Qwen3-4B-4bit-DWQ)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 4B 4bit DWQ Parameters and Internals

LLM NameQwen3 4B 4bit DWQ
Repository ๐Ÿค—https://huggingface.co/mlx-community/Qwen3-4B-4bit-DWQ 
Base Model(s)  Qwen/Qwen3-4B   Qwen/Qwen3-4B
Model Size4b
Required VRAM2.3 GB
Updated2025-07-25
Maintainermlx-community
Model Typeqwen3
Model Files  2.3 GB
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 4B 4bit DWQ

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 4B MLX 4bit64K / 2.1 GB2663
Qwen3 4B Unsloth Bnb 4bit40K / 3.6 GB685539
Qwen3 4B 4bit40K / 2.3 GB58717
Qwen3 4B 4bit DWQ 05312540K / 2.3 GB14742
...incot DPO 0720 Dataset V5 Dsr140K / 8.1 GB410
...d Qwen3 4B Abliterated V1 4bit40K / 2.3 GB9642
Qwen3 4B MLX 8bit40K / 4.2 GB1892
...d Qwen3 4B Abliterated V1 6bit40K / 3.3 GB692
Qwen3 4B 3kingdoms Augmented40K / 8.1 GB50
Qwen3 4B Base Unsloth Bnb 4bit32K / 3.3 GB98500
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3-4B-4bit-DWQ.

Rank the Qwen3 4B 4bit DWQ 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? 50035 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124