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 Instruct 2507 8bit by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen3 235B A22B Instruct 2507 8bit   URL Share it on

  60   
  8-bit   8bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3-235b-a22...   Conversational   Instruct   Mlx   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit 

Qwen3 235B A22B Instruct 2507 8bit Benchmarks

LLME Score: 0.25053
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 Instruct 2507 8bit (mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit)
🌟 Advertise your project 🚀

Qwen3 235B A22B Instruct 2507 8bit Parameters and Internals

LLM NameQwen3 235B A22B Instruct 2507 8bit
Repository 🤗https://huggingface.co/mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit 
Base Model(s)  Qwen3 235B A22B Instruct 2507   Qwen/Qwen3-235B-A22B-Instruct-2507
Model Size235b
Required VRAM227.7 GB
Updated2025-09-10
Maintainermlx-community
Model Typeqwen3_moe
Instruction-BasedYes
Model Files  5.1 GB: 1-of-48   5.3 GB: 2-of-48   5.3 GB: 3-of-48   5.3 GB: 4-of-48   5.3 GB: 5-of-48   5.3 GB: 6-of-48   5.3 GB: 7-of-48   5.3 GB: 8-of-48   5.3 GB: 9-of-48   5.3 GB: 10-of-48   5.3 GB: 11-of-48   5.3 GB: 12-of-48   5.3 GB: 13-of-48   5.3 GB: 14-of-48   5.3 GB: 15-of-48   5.3 GB: 16-of-48   5.3 GB: 17-of-48   5.3 GB: 18-of-48   5.3 GB: 19-of-48   5.3 GB: 20-of-48   5.3 GB: 21-of-48   5.3 GB: 22-of-48   5.3 GB: 23-of-48   5.3 GB: 24-of-48   5.3 GB: 25-of-48   5.3 GB: 26-of-48   5.3 GB: 27-of-48   5.3 GB: 28-of-48   5.3 GB: 29-of-48   5.3 GB: 30-of-48   5.3 GB: 31-of-48   5.3 GB: 32-of-48   5.3 GB: 33-of-48   5.3 GB: 34-of-48   5.3 GB: 35-of-48   5.3 GB: 36-of-48   5.3 GB: 37-of-48   5.3 GB: 38-of-48   5.3 GB: 39-of-48   5.3 GB: 40-of-48   5.3 GB: 41-of-48   5.3 GB: 42-of-48   5.3 GB: 43-of-48
Quantization Type8bit
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.51.0
Vocabulary Size151936
Torch Data Typebfloat16

Quantized Models of the Qwen3 235B A22B Instruct 2507 8bit

Model
Likes
Downloads
VRAM
...5B A22B Instruct 2507 3bit DWQ5243103 GB
...5B A22B Instruct 2507 4bit DWQ288131 GB

Best Alternatives to Qwen3 235B A22B Instruct 2507 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...5B A22B Instruct 2507 3bit DWQ256K / 103 GB2435
...5B A22B Instruct 2507 4bit DWQ256K / 131.4 GB882
...3 235B A22B Instruct 2507 4bit256K / 131.4 GB633
...en3 235B A22B Instruct 2507 1M986K / 171.9 GB161
Qwen3 235B A22B Instruct 2507256K / 471 GB92526671
...n3 235B A22B Instruct 2507 FP8256K / 236.5 GB32019121
...n3 235B A22B Instruct 2507 AWQ256K / 124.1 GB19204
Qwen3 235B A22B Instruct 2507256K / 471 GB5538
...n3 235B A22B Instruct 2507 FP8256K / 236.5 GB5553
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit.

Rank the Qwen3 235B A22B Instruct 2507 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? 51262 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