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 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen3 235B A22B 4bit   URL Share it on

  42042   
  4-bit   4bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3-235b-a22...   Conversational   Mlx   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3-235B-A22B-4bit 

Qwen3 235B A22B 4bit Benchmarks

LLME Score: 0.3538
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 4bit (mlx-community/Qwen3-235B-A22B-4bit)

Qwen3 235B A22B 4bit Parameters and Internals

LLM NameQwen3 235B A22B 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwen3-235B-A22B-4bit 
Base Model(s)  Qwen3 235B A22B   Qwen/Qwen3-235B-A22B
Model Size235b
Required VRAM131.4 GB
Updated2025-06-02
Maintainermlx-community
Model Typeqwen3_moe
Model Files  5.0 GB: 1-of-26   5.1 GB: 2-of-26   5.1 GB: 3-of-26   5.1 GB: 4-of-26   5.1 GB: 5-of-26   5.1 GB: 6-of-26   5.1 GB: 7-of-26   5.1 GB: 8-of-26   5.1 GB: 9-of-26   5.1 GB: 10-of-26   5.1 GB: 11-of-26   5.1 GB: 12-of-26   5.1 GB: 13-of-26   5.1 GB: 14-of-26   5.1 GB: 15-of-26   5.1 GB: 16-of-26   5.1 GB: 17-of-26   5.1 GB: 18-of-26   5.1 GB: 19-of-26   5.1 GB: 20-of-26   5.1 GB: 21-of-26   5.1 GB: 22-of-26   5.1 GB: 23-of-26   5.1 GB: 24-of-26   5.1 GB: 25-of-26   4.0 GB: 26-of-26
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 235B A22B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 235B A22B 8bit40K / 238.3 GB417112
Qwen3 235B A22B 3bit DWQ40K / 117.4 GB3432
Qwen3 235B A22B 4bit DWQ40K / 131.4 GB3512
Qwen3 235B A22B Mixed 3 6bit40K / 117 GB3112
Qwen3 235B A22B 128K GGUF128K /  GB11239930
Qwen3 235B A22B40K / 179.9 GB190055918
Qwen3 235B A22B FP840K / 225 GB5380370
Qwen3 235B A22B GGUF40K /  GB5518753
Qwen3 235B A22B GPTQ Int440K / 124.5 GB588813
Qwen3 235B A22B AWQ40K / 124.1 GB469210
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3-235B-A22B-4bit.

Rank the Qwen3 235B A22B 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? 47771 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