LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen3 30B A3B 4bit DWQ 05082025 by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen3 30B A3B 4bit DWQ 05082025   URL Share it on

  213   
  4-bit   4bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3-30b-a3b   Conversational   Mlx   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3-30B-A3B-4bit-DWQ-05082025 

Qwen3 30B A3B 4bit DWQ 05082025 Benchmarks

LLME Score: 0.313
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 30B A3B 4bit DWQ 05082025 (mlx-community/Qwen3-30B-A3B-4bit-DWQ-05082025)

Qwen3 30B A3B 4bit DWQ 05082025 Parameters and Internals

LLM NameQwen3 30B A3B 4bit DWQ 05082025
Repository 🤗https://huggingface.co/mlx-community/Qwen3-30B-A3B-4bit-DWQ-05082025 
Base Model(s)  Qwen3 30B A3B   Qwen/Qwen3-30B-A3B
Model Size30b
Required VRAM17.2 GB
Updated2025-05-17
Maintainermlx-community
Model Typeqwen3_moe
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.3 GB: 3-of-4   1.2 GB: 4-of-4
Quantization Type4bit
Model ArchitectureQwen3MoeForCausalLM
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 30B A3B 4bit DWQ 05082025

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 30B A3B MLX 4bit40K / 17.2 GB407819
Qwen3 30B A3B 4bit DWQ40K / 17.2 GB51019
Qwen3 30B A3B 4bit DWQ 050840K / 17.2 GB37411
Qwen3 30B A3B 4bit40K / 17.2 GB23057
Qwen3 30B A3B 8bit40K / 32.5 GB22555
Qwen3 30B A3B 6bit40K / 24.7 GB6762
Qwen3 30B A3B 128K GGUF128K / 9 GB4662440
...0B A6B 16 Extreme 128K Context128K / 61.1 GB447
Qwen3 30B A3B40K / 61.1 GB206712551
Qwen3 30B A3B GGUF40K / 9 GB250497167
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3-30B-A3B-4bit-DWQ-05082025.

Rank the Qwen3 30B A3B 4bit DWQ 05082025 Capabilities

🆘 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! 🌟

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? 47402 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer