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

Qwen3 Coder 480B A35B Instruct by Qwen

 »  All LLMs  »  Qwen  »  Qwen3 Coder 480B A35B Instruct   URL Share it on

  29491   

Qwen3 Coder 480B A35B Instruct is an open-source language model by Qwen. Features: 480b LLM, VRAM: 171.9GB, Context: 256K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.32.

  Arxiv:2505.09388   Codegen   Conversational   Endpoints compatible   Eval-results   Instruct   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct 

Qwen3 Coder 480B A35B Instruct Benchmarks

LLME Score: 0.32172
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 (Qwen/Qwen3-Coder-480B-A35B-Instruct)

Qwen3 Coder 480B A35B Instruct Parameters and Internals

LLM NameQwen3 Coder 480B A35B Instruct
Repository 🤗https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct 
Model Size480b
Required VRAM171.9 GB
Updated2026-07-23
MaintainerQwen
Model Typeqwen3_moe
Instruction-BasedYes
Model Files  4.0 GB: 1-of-241   4.0 GB: 2-of-241   4.0 GB: 3-of-241   4.0 GB: 4-of-241   4.0 GB: 5-of-241   4.0 GB: 6-of-241   4.0 GB: 7-of-241   4.0 GB: 8-of-241   4.0 GB: 9-of-241   4.0 GB: 10-of-241   4.0 GB: 11-of-241   4.0 GB: 12-of-241   4.0 GB: 13-of-241   4.0 GB: 14-of-241   4.0 GB: 15-of-241   3.9 GB: 16-of-241   4.0 GB: 17-of-241   4.0 GB: 18-of-241   4.0 GB: 19-of-241   4.0 GB: 20-of-241   4.0 GB: 21-of-241   4.0 GB: 22-of-241   4.0 GB: 23-of-241   4.0 GB: 24-of-241   4.0 GB: 25-of-241   4.0 GB: 26-of-241   4.0 GB: 27-of-241   4.0 GB: 28-of-241   4.0 GB: 29-of-241   4.0 GB: 30-of-241   4.0 GB: 31-of-241   4.0 GB: 32-of-241   4.0 GB: 33-of-241   4.0 GB: 34-of-241   4.0 GB: 35-of-241   4.0 GB: 36-of-241   4.0 GB: 37-of-241   4.0 GB: 38-of-241   4.0 GB: 39-of-241   4.0 GB: 40-of-241   4.0 GB: 41-of-241   4.0 GB: 42-of-241   4.0 GB: 43-of-241
Generates CodeYes
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.51.0
Vocabulary Size151936
Torch Data Typebfloat16

Quantized Models of the Qwen3 Coder 480B A35B Instruct

Model
Likes
Downloads
VRAM
... Coder 480B A35B Instruct 4bit193361185 GB

Best Alternatives to Qwen3 Coder 480B A35B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
...n3 Coder 480B A35B Instruct 1M1024K / 171.9 GB148
Qwen3 Coder 480B A35B Instruct256K / 167.9 GB355
...3 Coder 480B A35B Instruct FP8256K / 429.8 GB154455156
...Coder 480B A35B Instruct NVFP4256K / 210 GB76812
Qwen3 Coder REAP 363B A35B256K / 215 GB2025
...3 Coder 480B A35B Instruct FP8256K / 429.8 GB598
... Coder 480B A35B Instruct 4bit256K / 185.6 GB336119
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-Coder-480B-A35B-Instruct.

Rank the Qwen3 Coder 480B A35B Instruct 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? 55558 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