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

Hy3 NVFP4 W4A16 by kodelow

 »  All LLMs  »  kodelow  »  Hy3 NVFP4 W4A16   URL Share it on

  20   

Hy3 NVFP4 W4A16 is an open-source language model by kodelow. Features: 172b LLM, VRAM: 79.7GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.29.

  8-bit Base model:quantized:tencent/h...   Base model:tencent/hy3   Compressed-tensors   Conversational   Endpoints compatible   Hunyuan   Hy3   Hy v3   Moe   Nvfp4   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/kodelow/Hy3-NVFP4-W4A16 

Hy3 NVFP4 W4A16 Benchmarks

LLME Score: 0.29275
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hy3 NVFP4 W4A16 (kodelow/Hy3-NVFP4-W4A16)
🌟 Advertise your project 🚀

Hy3 NVFP4 W4A16 Parameters and Internals

LLM NameHy3 NVFP4 W4A16
Repository 🤗https://huggingface.co/kodelow/Hy3-NVFP4-W4A16 
Base Model(s)  Hy3   tencent/Hy3
Model Size172b
Required VRAM79.7 GB
Updated2026-07-08
Maintainerkodelow
Model Typehy_v3
Model Files  2.0 GB: 1-of-99   2.0 GB: 2-of-99   2.0 GB: 3-of-99   2.0 GB: 4-of-99   2.0 GB: 5-of-99   1.1 GB: 6-of-99   2.0 GB: 7-of-99   2.0 GB: 8-of-99   2.0 GB: 9-of-99   2.0 GB: 10-of-99   2.0 GB: 11-of-99   1.1 GB: 12-of-99   2.0 GB: 13-of-99   2.0 GB: 14-of-99   2.0 GB: 15-of-99   2.0 GB: 16-of-99   2.0 GB: 17-of-99   1.1 GB: 18-of-99   2.0 GB: 19-of-99   2.0 GB: 20-of-99   2.0 GB: 21-of-99   2.0 GB: 22-of-99   2.0 GB: 23-of-99   1.1 GB: 24-of-99   2.0 GB: 25-of-99   2.0 GB: 26-of-99   2.0 GB: 27-of-99   2.0 GB: 28-of-99   2.0 GB: 29-of-99   1.1 GB: 30-of-99   2.0 GB: 31-of-99   2.0 GB: 32-of-99   2.0 GB: 33-of-99   2.0 GB: 34-of-99   2.0 GB: 35-of-99   1.1 GB: 36-of-99   2.0 GB: 37-of-99   2.0 GB: 38-of-99   2.0 GB: 39-of-99   2.0 GB: 40-of-99   2.0 GB: 41-of-99   1.1 GB: 42-of-99   2.0 GB: 43-of-99
Model ArchitectureHYV3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.6.0
Vocabulary Size120832

Best Alternatives to Hy3 NVFP4 W4A16

Best Alternatives
Context / RAM
Downloads
Likes
SuperHY3 Abliterated NVFP4256K / 66.6 GB88
Note: green Score (e.g. "73.2") means that the model is better than kodelow/Hy3-NVFP4-W4A16.

Rank the Hy3 NVFP4 W4A16 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? 55114 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