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

Qwen3 Coder 480B A35B Instruct 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen3 Coder 480B A35B Instruct 4bit   URL Share it on

  1448   
  4-bit   4bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3-coder-48...   Codegen   Conversational   Instruct   Mlx   Quantized   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit 

Qwen3 Coder 480B A35B Instruct 4bit Benchmarks

LLME Score: 0.38869
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 Coder 480B A35B Instruct 4bit (mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit)
🌟 Advertise your project 🚀

Qwen3 Coder 480B A35B Instruct 4bit Parameters and Internals

LLM NameQwen3 Coder 480B A35B Instruct 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit 
Base Model(s)  Qwen3 Coder 480B A35B Instruct   Qwen/Qwen3-Coder-480B-A35B-Instruct
Model Size480b
Required VRAM185.6 GB
Updated2025-07-25
Maintainermlx-community
Model Typeqwen3_moe
Instruction-BasedYes
Model Files  5.0 GB: 1-of-62   4.3 GB: 2-of-62   4.3 GB: 3-of-62   4.3 GB: 4-of-62   4.3 GB: 5-of-62   4.3 GB: 6-of-62   4.3 GB: 7-of-62   4.3 GB: 8-of-62   4.3 GB: 9-of-62   4.3 GB: 10-of-62   4.3 GB: 11-of-62   4.3 GB: 12-of-62   4.3 GB: 13-of-62   4.3 GB: 14-of-62   4.3 GB: 15-of-62   4.3 GB: 16-of-62   4.3 GB: 17-of-62   4.3 GB: 18-of-62   4.3 GB: 19-of-62   4.3 GB: 20-of-62   4.3 GB: 21-of-62   4.3 GB: 22-of-62   4.3 GB: 23-of-62   4.3 GB: 24-of-62   4.3 GB: 25-of-62   4.3 GB: 26-of-62   4.3 GB: 27-of-62   4.3 GB: 28-of-62   4.3 GB: 29-of-62   4.3 GB: 30-of-62   4.3 GB: 31-of-62   4.3 GB: 32-of-62   4.3 GB: 33-of-62   4.3 GB: 34-of-62   4.3 GB: 35-of-62   4.3 GB: 36-of-62   4.3 GB: 37-of-62   4.3 GB: 38-of-62   4.3 GB: 39-of-62   4.3 GB: 40-of-62   4.3 GB: 41-of-62   4.3 GB: 42-of-62   4.3 GB: 43-of-62
Quantization Type4bit
Generates CodeYes
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.51.0
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to Qwen3 Coder 480B A35B Instruct 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 Coder 480B A35B Instruct256K / 179.9 GB2711623
...3 Coder 480B A35B Instruct FP8256K / 439.8 GB416753
...3 Coder 480B A35B Instruct FP8256K / 429.8 GB352
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit.

Rank the Qwen3 Coder 480B A35B Instruct 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? 50068 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