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 NVFP4 by nvidia

 »  All LLMs  »  nvidia  »  Qwen3 Coder 480B A35B Instruct NVFP4   URL Share it on

  768   

Qwen3 Coder 480B A35B Instruct NVFP4 is an open-source language model by nvidia. Features: 480b LLM, VRAM: 210GB, Context: 256K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.24.

  8-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3-coder-48...   Codegen   Conversational   Fp4   Instruct   Model optimizer   Modelopt   Nvidia   Quantized   Qwen3   Qwen3 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/Qwen3-Coder-480B-A35B-Instruct-NVFP4 

Qwen3 Coder 480B A35B Instruct NVFP4 Benchmarks

LLME Score: 0.24341
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 NVFP4 (nvidia/Qwen3-Coder-480B-A35B-Instruct-NVFP4)

Qwen3 Coder 480B A35B Instruct NVFP4 Parameters and Internals

LLM NameQwen3 Coder 480B A35B Instruct NVFP4
Repository 🤗https://huggingface.co/nvidia/Qwen3-Coder-480B-A35B-Instruct-NVFP4 
Base Model(s)  Qwen3 Coder 480B A35B Instruct   Qwen/Qwen3-Coder-480B-A35B-Instruct
Model Size480b
Required VRAM210 GB
Updated2026-06-30
Maintainernvidia
Model Typeqwen3_moe
Instruction-BasedYes
Model Files  5.0 GB: 1-of-55   5.0 GB: 2-of-55   5.0 GB: 3-of-55   5.0 GB: 4-of-55   5.0 GB: 5-of-55   5.0 GB: 6-of-55   5.0 GB: 7-of-55   5.0 GB: 8-of-55   5.0 GB: 9-of-55   5.0 GB: 10-of-55   5.0 GB: 11-of-55   5.0 GB: 12-of-55   5.0 GB: 13-of-55   5.0 GB: 14-of-55   5.0 GB: 15-of-55   5.0 GB: 16-of-55   5.0 GB: 17-of-55   5.0 GB: 18-of-55   5.0 GB: 19-of-55   5.0 GB: 20-of-55   5.0 GB: 21-of-55   5.0 GB: 22-of-55   5.0 GB: 23-of-55   5.0 GB: 24-of-55   5.0 GB: 25-of-55   5.0 GB: 26-of-55   5.0 GB: 27-of-55   5.0 GB: 28-of-55   5.0 GB: 29-of-55   5.0 GB: 30-of-55   5.0 GB: 31-of-55   5.0 GB: 32-of-55   5.0 GB: 33-of-55   5.0 GB: 34-of-55   5.0 GB: 35-of-55   5.0 GB: 36-of-55   5.0 GB: 37-of-55   5.0 GB: 38-of-55   5.0 GB: 39-of-55   5.0 GB: 40-of-55   5.0 GB: 41-of-55   5.0 GB: 42-of-55
Generates CodeYes
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.56.0
Vocabulary Size151936

Best Alternatives to Qwen3 Coder 480B A35B Instruct NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
...n3 Coder 480B A35B Instruct 1M1024K / 171.9 GB148
Qwen3 Coder 480B A35B Instruct256K / 167.9 GB355
Qwen3 Coder 480B A35B Instruct256K / 171.9 GB294911356
...3 Coder 480B A35B Instruct FP8256K / 429.8 GB154455156
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 nvidia/Qwen3-Coder-480B-A35B-Instruct-NVFP4.

Rank the Qwen3 Coder 480B A35B Instruct NVFP4 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