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

Qwen3 Next 80B A3B Thinking by Qwen

 »  All LLMs  »  Qwen  »  Qwen3 Next 80B A3B Thinking   URL Share it on

  35972   

Qwen3 Next 80B A3B Thinking is an open-source language model by Qwen. Features: 80b LLM, VRAM: 162.7GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.36.

  Arxiv:2309.00071   Arxiv:2501.15383   Arxiv:2505.09388   Conversational   Deploy:azure   Endpoints compatible   Eval-results   Qwen3 next   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking 

Qwen3 Next 80B A3B Thinking Benchmarks

LLME Score: 0.35751
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 Next 80B A3B Thinking (Qwen/Qwen3-Next-80B-A3B-Thinking)
🌟 Advertise your project 🚀

Qwen3 Next 80B A3B Thinking Parameters and Internals

LLM NameQwen3 Next 80B A3B Thinking
Repository 🤗https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking 
Model Size80b
Required VRAM162.7 GB
Updated2026-04-14
MaintainerQwen
Model Typeqwen3_next
Model Files  4.0 GB: 1-of-41   4.0 GB: 2-of-41   4.0 GB: 3-of-41   4.0 GB: 4-of-41   4.0 GB: 5-of-41   4.0 GB: 6-of-41   4.0 GB: 7-of-41   4.0 GB: 8-of-41   4.0 GB: 9-of-41   4.0 GB: 10-of-41   4.0 GB: 11-of-41   4.0 GB: 12-of-41   4.0 GB: 13-of-41   4.0 GB: 14-of-41   4.0 GB: 15-of-41   4.0 GB: 16-of-41   4.0 GB: 17-of-41   4.0 GB: 18-of-41   4.0 GB: 19-of-41   4.0 GB: 20-of-41   4.0 GB: 21-of-41   4.0 GB: 22-of-41   4.0 GB: 23-of-41   4.0 GB: 24-of-41   4.0 GB: 25-of-41   4.0 GB: 26-of-41   4.0 GB: 27-of-41   4.0 GB: 28-of-41   4.0 GB: 29-of-41   4.0 GB: 30-of-41   4.0 GB: 31-of-41   4.0 GB: 32-of-41   4.0 GB: 33-of-41   4.0 GB: 34-of-41   4.0 GB: 35-of-41   4.0 GB: 36-of-41   4.0 GB: 37-of-41   4.0 GB: 38-of-41   4.0 GB: 39-of-41   3.4 GB: 40-of-41   3.3 GB: 41-of-41
Model ArchitectureQwen3NextForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen3 Next 80B A3B Thinking

Model
Likes
Downloads
VRAM
...Next 80B A3B Thinking AWQ 4bit2312537549 GB
...Next 80B A3B Thinking AWQ 4bit113614947 GB
...en3 Next 80B A3B Thinking 8bit21045383 GB
...en3 Next 80B A3B Thinking 4bit2151244 GB

Best Alternatives to Qwen3 Next 80B A3B Thinking

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 Next 80B A3B Instruct256K / 162.7 GB1398721855
Qwen3 Next 80B A3B Instruct256K / 162.7 GB312673
Qwen3 Next 80B A3B Thinking256K / 162.7 GB367
...n3 Next 80B A3B Thinking NVFP4256K / 50.7 GB11104953
...wen3 Next 80B A3B Instruct FP8256K / 81.8 GB19060085
...n3 Next 80B A3B Instruct NVFP4256K / 50.7 GB2020637
...wen3 Next 80B A3B Thinking FP8256K / 81.8 GB2447352
Qwen3 Next MoE256K / 0 GB156434
... Instruct Int4 Mixed AutoRound256K / 43.1 GB12923
...ext 80B A3B Instruct Mxfp4 Mlx256K / 42 GB2288
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen3-Next-80B-A3B-Thinking.

Rank the Qwen3 Next 80B A3B Thinking 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? 53026 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer