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 Thinking 2507 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen3 30B A3B Thinking 2507 4bit   URL Share it on

  127   

Qwen3 30B A3B Thinking 2507 4bit is an open-source language model by mlx-community. Features: 30b LLM, VRAM: 17.2GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.21.

  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-Thinking-2507-4bit 

Qwen3 30B A3B Thinking 2507 4bit Benchmarks

LLME Score: 0.21307
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 Thinking 2507 4bit (mlx-community/Qwen3-30B-A3B-Thinking-2507-4bit)
🌟 Advertise your project 🚀

Qwen3 30B A3B Thinking 2507 4bit Parameters and Internals

LLM NameQwen3 30B A3B Thinking 2507 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwen3-30B-A3B-Thinking-2507-4bit 
Base Model(s)  Qwen3 30B A3B Thinking 2507   Qwen/Qwen3-30B-A3B-Thinking-2507
Model Size30b
Required VRAM17.2 GB
Updated2026-04-14
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 Length262144
Model Max Length262144
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 30B A3B Thinking 2507 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...30B A3B Instruct 2507 MLX 8bit256K / 32.5 GB736434
...30B A3B Instruct 2507 MLX 4bit256K / 17.2 GB351066
...n3 Coder 30B A3B Instruct 4bit256K / 17.2 GB251414
...n3 Coder 30B A3B Instruct 8bit256K / 32.5 GB13026
...30B A3B Thinking 2507 MLX 4bit256K / 17.2 GB10072
...r 30B A3B Instruct 4bit Dwq V2256K / 17.2 GB5808
...en3 30B A3B Instruct 2507 4bit256K / 17.2 GB4259
...oder 30B A3B Instruct 4bit DWQ256K / 17.2 GB5105
...en3 30B A3B Instruct 2507 8bit256K / 32.5 GB642
Qwen3 30B A3B 128K Bnb 4bit128K / 16.7 GB60
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3-30B-A3B-Thinking-2507-4bit.

Rank the Qwen3 30B A3B Thinking 2507 4bit 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? 53089 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