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 FP8 by unsloth

 »  All LLMs  »  unsloth  »  Qwen3 Coder Next FP8   URL Share it on

  25894   

Qwen3 Coder Next FP8 is an open-source language model by unsloth. Features: LLM, VRAM: 80.3GB, Context: 256K, License: apache-2.0, Code Generating, LLM Explorer Score: 0.34.

Base model:quantized:qwen/qwen... Base model:qwen/qwen3-coder-ne...   Codegen   Conversational   Endpoints compatible   Fp8   Qwen   Qwen3   Qwen3 next   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3-Coder-Next-FP8 

Qwen3 Coder Next FP8 Benchmarks

LLME Score: 0.34055
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 FP8 (unsloth/Qwen3-Coder-Next-FP8)
🌟 Advertise your project 🚀

Qwen3 Coder Next FP8 Parameters and Internals

LLM NameQwen3 Coder Next FP8
Repository 🤗https://huggingface.co/unsloth/Qwen3-Coder-Next-FP8 
Base Model(s)  Qwen/Qwen3-Coder-Next   Qwen/Qwen3-Coder-Next
Required VRAM80.3 GB
Updated2026-03-27
Maintainerunsloth
Model Typeqwen3_next
Model Files  2.3 GB: 1-of-40   2.0 GB: 2-of-40   2.0 GB: 3-of-40   2.0 GB: 4-of-40   2.0 GB: 5-of-40   2.0 GB: 6-of-40   2.0 GB: 7-of-40   2.0 GB: 8-of-40   2.0 GB: 9-of-40   2.0 GB: 10-of-40   2.0 GB: 11-of-40   2.0 GB: 12-of-40   2.0 GB: 13-of-40   2.0 GB: 14-of-40   2.0 GB: 15-of-40   2.0 GB: 16-of-40   2.0 GB: 17-of-40   2.0 GB: 18-of-40   2.0 GB: 19-of-40   2.0 GB: 20-of-40   2.0 GB: 21-of-40   2.0 GB: 22-of-40   2.0 GB: 23-of-40   2.0 GB: 24-of-40   2.0 GB: 25-of-40   2.0 GB: 26-of-40   2.0 GB: 27-of-40   2.0 GB: 28-of-40   2.0 GB: 29-of-40   2.0 GB: 30-of-40   2.0 GB: 31-of-40   2.0 GB: 32-of-40   2.0 GB: 33-of-40   2.0 GB: 34-of-40   2.0 GB: 35-of-40   2.0 GB: 36-of-40   2.0 GB: 37-of-40   2.0 GB: 38-of-40   2.0 GB: 39-of-40   2.0 GB: 40-of-40
Generates CodeYes
Model ArchitectureQwen3NextForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.6
Vocabulary Size151936
Torch Data Typebfloat16

Best Alternatives to Qwen3 Coder Next FP8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 Coder Next 4bit256K / 44.9 GB659012

Rank the Qwen3 Coder Next FP8 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? 52052 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 v20260327b
  Support LLM Explorer