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

Qwen3 235B A22B MLX 8bit by Qwen

 »  All LLMs  »  Qwen  »  Qwen3 235B A22B MLX 8bit   URL Share it on

  168   

Qwen3 235B A22B MLX 8bit is an open-source language model by Qwen. Features: 235b LLM, VRAM: 229.3GB, Context: 40K, License: apache-2.0, Quantized, LLM Explorer Score: 0.19.

  Arxiv:2309.00071   Arxiv:2505.09388   8-bit   8bit   Conversational   Mlx   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-235B-A22B-MLX-8bit 

Qwen3 235B A22B MLX 8bit Benchmarks

LLME Score: 0.19207
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 8bit (Qwen/Qwen3-235B-A22B-MLX-8bit)

Qwen3 235B A22B MLX 8bit Parameters and Internals

LLM NameQwen3 235B A22B MLX 8bit
Repository 🤗https://huggingface.co/Qwen/Qwen3-235B-A22B-MLX-8bit 
Model Size235b
Required VRAM229.3 GB
Updated2026-07-12
MaintainerQwen
Model Typeqwen3_moe
Model Files  4.9 GB: 1-of-48   5.1 GB: 2-of-48   5.1 GB: 3-of-48   5.1 GB: 4-of-48   5.1 GB: 5-of-48   5.1 GB: 6-of-48   5.1 GB: 7-of-48   5.1 GB: 8-of-48   5.1 GB: 9-of-48   5.1 GB: 10-of-48   5.1 GB: 11-of-48   5.1 GB: 12-of-48   5.1 GB: 13-of-48   5.1 GB: 14-of-48   5.1 GB: 15-of-48   5.1 GB: 16-of-48   5.1 GB: 17-of-48   5.1 GB: 18-of-48   5.1 GB: 19-of-48   5.1 GB: 20-of-48   5.1 GB: 21-of-48   5.1 GB: 22-of-48   5.1 GB: 23-of-48   5.1 GB: 24-of-48   5.1 GB: 25-of-48   5.1 GB: 26-of-48   5.1 GB: 27-of-48   5.1 GB: 28-of-48   5.1 GB: 29-of-48   5.1 GB: 30-of-48   5.1 GB: 31-of-48   5.1 GB: 32-of-48   5.1 GB: 33-of-48   5.1 GB: 34-of-48   5.1 GB: 35-of-48   5.1 GB: 36-of-48   5.1 GB: 37-of-48   5.1 GB: 38-of-48   5.1 GB: 39-of-48   5.1 GB: 40-of-48   5.1 GB: 41-of-48   5.1 GB: 42-of-48   5.1 GB: 43-of-48   5.1 GB: 44-of-48   5.1 GB: 45-of-48
Quantization Type8bit
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.0
Vocabulary Size151936
Torch Data Typefloat16

Best Alternatives to Qwen3 235B A22B MLX 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...3 235B A22B Instruct 2507 4bit256K / 131.4 GB39073
...3 235B A22B Instruct 2507 8bit256K / 227.7 GB37422
...3 235B A22B Thinking 2507 8bit256K / 227.7 GB4124
...5B A22B Thinking 2507 3bit DWQ256K / 103 GB2046
...5B A22B Instruct 2507 3bit DWQ256K / 103 GB1745
...5B A22B Thinking 2507 4bit DWQ256K / 131.4 GB804
...5B A22B Instruct 2507 4bit DWQ256K / 131.4 GB712
Qwen3 235B A22B 4bit40K / 131.4 GB24989
Qwen3 235B A22B 8bit40K / 238.3 GB20424
Qwen3 235B A22B MLX 4bit40K / 125.2 GB39916
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-235B-A22B-MLX-8bit.

Rank the Qwen3 235B A22B MLX 8bit 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? 55396 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer