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

Qwen3.5 397B A17B Nvfp4 by mlx-community

 »  All LLMs  »  mlx-community  »  Qwen3.5 397B A17B Nvfp4   URL Share it on

  1788   

Qwen3.5 397B A17B Nvfp4 is an open-source language model by mlx-community. Features: 397b LLM, VRAM: 221.3GB, License: apache-2.0, LLM Explorer Score: 0.3.

  4-bit   4bit   Apple-silicon Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-397b-a...   Conversational   Mixture-of-experts   Mlx   Moe   Multilingual   Nvfp4   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.5-397B-A17B-nvfp4 

Qwen3.5 397B A17B Nvfp4 Benchmarks

LLME Score: 0.29741
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3.5 397B A17B Nvfp4 (mlx-community/Qwen3.5-397B-A17B-nvfp4)
🌟 Advertise your project 🚀

Qwen3.5 397B A17B Nvfp4 Parameters and Internals

LLM NameQwen3.5 397B A17B Nvfp4
Repository 🤗https://huggingface.co/mlx-community/Qwen3.5-397B-A17B-nvfp4 
Base Model(s)  Qwen/Qwen3.5-397B-A17B   Qwen/Qwen3.5-397B-A17B
Model Size397b
Required VRAM221.3 GB
Updated2026-03-27
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  4.3 GB: 1-of-46   4.9 GB: 2-of-46   4.9 GB: 3-of-46   5.0 GB: 4-of-46   4.9 GB: 5-of-46   4.9 GB: 6-of-46   5.0 GB: 7-of-46   4.9 GB: 8-of-46   4.9 GB: 9-of-46   5.0 GB: 10-of-46   4.9 GB: 11-of-46   4.9 GB: 12-of-46   5.0 GB: 13-of-46   4.9 GB: 14-of-46   4.9 GB: 15-of-46   5.0 GB: 16-of-46   4.9 GB: 17-of-46   4.9 GB: 18-of-46   5.0 GB: 19-of-46   4.9 GB: 20-of-46   4.9 GB: 21-of-46   5.0 GB: 22-of-46   4.9 GB: 23-of-46   4.9 GB: 24-of-46   5.0 GB: 25-of-46   4.9 GB: 26-of-46   4.9 GB: 27-of-46   5.0 GB: 28-of-46   4.9 GB: 29-of-46   4.9 GB: 30-of-46   5.0 GB: 31-of-46   4.9 GB: 32-of-46   4.9 GB: 33-of-46   5.0 GB: 34-of-46   4.9 GB: 35-of-46   4.9 GB: 36-of-46   5.0 GB: 37-of-46   4.9 GB: 38-of-46   4.9 GB: 39-of-46   5.0 GB: 40-of-46   4.9 GB: 41-of-46   4.9 GB: 42-of-46   5.0 GB: 43-of-46   4.9 GB: 44-of-46   4.9 GB: 45-of-46
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Transformers Version4.57.0.dev0

Best Alternatives to Qwen3.5 397B A17B Nvfp4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 397B A17B NVFP40K / 251.1 GB42674688
...7B A17B Heretic Int4 AutoRound0K / 212.3 GB412
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.5-397B-A17B-nvfp4.

Rank the Qwen3.5 397B A17B 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? 52721 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