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 Coder Next by Qwen

 »  All LLMs  »  Qwen  »  Qwen3 Coder Next   URL Share it on

  1024925   

Qwen3 Coder Next is an open-source language model by Qwen. Features: 79.7b LLM, VRAM: 159.4GB, Context: 256K, License: apache-2.0, Code Generating, LLM Explorer Score: 0.5.

  Codegen   Conversational   Deploy:azure   Endpoints compatible   Eval-results   Qwen3 next   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen3-Coder-Next 

Qwen3 Coder Next Benchmarks

LLME Score: 0.50013
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 Coder Next (Qwen/Qwen3-Coder-Next)
🌟 Advertise your project 🚀

Qwen3 Coder Next Parameters and Internals

LLM NameQwen3 Coder Next
Repository 🤗https://huggingface.co/Qwen/Qwen3-Coder-Next 
Model Size79.7b
Required VRAM159.4 GB
Updated2026-05-05
MaintainerQwen
Model Typeqwen3_next
Model Files  4.0 GB: 1-of-40   4.0 GB: 2-of-40   4.0 GB: 3-of-40   4.0 GB: 4-of-40   4.0 GB: 5-of-40   4.0 GB: 6-of-40   4.0 GB: 7-of-40   4.0 GB: 8-of-40   4.0 GB: 9-of-40   4.0 GB: 10-of-40   4.0 GB: 11-of-40   4.0 GB: 12-of-40   4.0 GB: 13-of-40   4.0 GB: 14-of-40   4.0 GB: 15-of-40   4.0 GB: 16-of-40   4.0 GB: 17-of-40   4.0 GB: 18-of-40   4.0 GB: 19-of-40   4.0 GB: 20-of-40   4.0 GB: 21-of-40   4.0 GB: 22-of-40   4.0 GB: 23-of-40   4.0 GB: 24-of-40   4.0 GB: 25-of-40   4.0 GB: 26-of-40   4.0 GB: 27-of-40   4.0 GB: 28-of-40   4.0 GB: 29-of-40   4.0 GB: 30-of-40   4.0 GB: 31-of-40   4.0 GB: 32-of-40   4.0 GB: 33-of-40   4.0 GB: 34-of-40   4.0 GB: 35-of-40   4.0 GB: 36-of-40   4.0 GB: 37-of-40   4.0 GB: 38-of-40   4.0 GB: 39-of-40   3.4 GB: 40-of-40
Generates CodeYes
Model ArchitectureQwen3NextForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.0.dev0
Vocabulary Size151936
Torch Data Typebfloat16

Quantized Models of the Qwen3 Coder Next

Model
Likes
Downloads
VRAM
Qwen3 Coder Next 4bit20737044 GB
Qwen3 Coder Next 8bit13519683 GB
Qwen3 Coder Next 5bit2206254 GB

Best Alternatives to Qwen3 Coder Next

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 Coder Next FP8256K / 80.3 GB273781142
Qwen3 Coder Next FP8 Dynamic256K / 83.4 GB1513641
Qwen3 Coder Next256K / 159.4 GB1871526
Qwen3 Coder Next Base256K / 159.4 GB119266
Qwen3 Coder Next Bf16256K / 159.7 GB21762
Qwen3 Coder Next 8bit256K / 83.9 GB519613
Qwen3 Coder Next 5bit256K / 54.9 GB20622

Rank the Qwen3 Coder Next 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? 53651 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