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

Qwen3 30B A3B MLX 6bit by Qwen

 »  All LLMs  »  Qwen  »  Qwen3 30B A3B MLX 6bit   URL Share it on

  52   

Qwen3 30B A3B MLX 6bit is an open-source language model by Qwen. Features: 30b LLM, VRAM: 24GB, Context: 40K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.

  Arxiv:2309.00071   Arxiv:2505.09388   6-bit   6bit   Conversational   Mlx   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-30B-A3B-MLX-6bit 

Qwen3 30B A3B MLX 6bit Benchmarks

LLME Score: 0.19162
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 MLX 6bit (Qwen/Qwen3-30B-A3B-MLX-6bit)
🌟 Advertise your project 🚀

Qwen3 30B A3B MLX 6bit Parameters and Internals

LLM NameQwen3 30B A3B MLX 6bit
Repository 🤗https://huggingface.co/Qwen/Qwen3-30B-A3B-MLX-6bit 
Model Size30b
Required VRAM24 GB
Updated2026-06-27
MaintainerQwen
Model Typeqwen3_moe
Model Files  5.3 GB: 1-of-5   5.4 GB: 2-of-5   5.4 GB: 3-of-5   5.4 GB: 4-of-5   2.5 GB: 5-of-5
Quantization Type6bit
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 MLX 6bit

Best Alternatives
Context / RAM
Downloads
Likes
...30B A3B Instruct 2507 MLX 8bit256K / 32.5 GB736434
...30B A3B Instruct 2507 MLX 4bit256K / 17.2 GB309048
...n3 Coder 30B A3B Instruct 4bit256K / 17.2 GB515820
...en3 30B A3B Instruct 2507 4bit256K / 17.2 GB216810
...r 30B A3B Instruct 4bit Dwq V2256K / 17.2 GB13959
...n3 Coder 30B A3B Instruct 8bit256K / 32.5 GB14106
...oder 30B A3B Instruct 4bit DWQ256K / 17.2 GB6715
...30B A3B Thinking 2507 MLX 4bit256K / 17.2 GB5871
...en3 30B A3B Thinking 2507 4bit256K / 17.2 GB2904
...en3 30B A3B Instruct 2507 8bit256K / 32.5 GB1162
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-30B-A3B-MLX-6bit.

Rank the Qwen3 30B A3B MLX 6bit 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? 54702 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer