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

Qwen3 235B A22B MLX 4bit by Qwen

 »  All LLMs  »  Qwen  »  Qwen3 235B A22B MLX 4bit   URL Share it on

  1455   
  Arxiv:2309.00071   Arxiv:2505.09388   4-bit   4bit   Conversational   Mlx   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-235B-A22B-MLX-4bit 

Qwen3 235B A22B MLX 4bit Benchmarks

LLME Score: 0.2792
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 235B A22B MLX 4bit (Qwen/Qwen3-235B-A22B-MLX-4bit)
🌟 Advertise your project 🚀

Qwen3 235B A22B MLX 4bit Parameters and Internals

LLM NameQwen3 235B A22B MLX 4bit
Repository 🤗https://huggingface.co/Qwen/Qwen3-235B-A22B-MLX-4bit 
Model Size235b
Required VRAM125.2 GB
Updated2025-08-31
MaintainerQwen
Model Typeqwen3_moe
Model Files  5.2 GB: 1-of-24   5.3 GB: 2-of-24   5.3 GB: 3-of-24   5.3 GB: 4-of-24   5.3 GB: 5-of-24   5.3 GB: 6-of-24   5.3 GB: 7-of-24   5.3 GB: 8-of-24   5.3 GB: 9-of-24   5.3 GB: 10-of-24   5.3 GB: 11-of-24   5.3 GB: 12-of-24   5.3 GB: 13-of-24   5.3 GB: 14-of-24   5.3 GB: 15-of-24   5.3 GB: 16-of-24   5.3 GB: 17-of-24   5.3 GB: 18-of-24   5.3 GB: 19-of-24   5.3 GB: 20-of-24   5.3 GB: 21-of-24   5.3 GB: 22-of-24   5.3 GB: 23-of-24   3.4 GB: 24-of-24
Quantization Type4bit
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.3
Tokenizer ClassQwen2Tokenizer
Padding Token<unk>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen3 235B A22B MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...5B A22B Thinking 2507 3bit DWQ256K / 103 GB5456
...5B A22B Thinking 2507 4bit DWQ256K / 131.4 GB3714
...5B A22B Instruct 2507 3bit DWQ256K / 103 GB3445
...5B A22B Instruct 2507 4bit DWQ256K / 131.4 GB1802
...3 235B A22B Instruct 2507 4bit256K / 131.4 GB733
...3 235B A22B Instruct 2507 8bit256K / 227.7 GB780
Qwen3 235B A22B 4bit40K / 131.4 GB104217
Qwen3 235B A22B 8bit40K / 238.3 GB103053
Qwen3 235B A22B 3bit DWQ40K / 117.4 GB11835
Qwen3 235B A22B 4bit DWQ40K / 131.4 GB10982
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-235B-A22B-MLX-4bit.

Rank the Qwen3 235B A22B MLX 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? 51022 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 v20241124
  Support LLM Explorer