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 GPTQ RTN 4bit Tp8 by avtc

 »  All LLMs  »  avtc  »  Hy3 GPTQ RTN 4bit Tp8   URL Share it on

  46   

Hy3 GPTQ RTN 4bit Tp8 is an open-source language model by avtc. Features: 295b LLM, VRAM: 161.3GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  4-bit   4bit Base model:quantized:tencent/h...   Base model:tencent/hy3   Conversational   Gptq   Hunyuan   Hy3   Hy v3   Moe   Quantization   Quantized   Region:us   Rtn   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/avtc/Hy3-GPTQ-RTN-4bit-tp8 

Hy3 GPTQ RTN 4bit Tp8 Benchmarks

LLME Score: 0.31718
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hy3 GPTQ RTN 4bit Tp8 (avtc/Hy3-GPTQ-RTN-4bit-tp8)
🌟 Advertise your project 🚀

Hy3 GPTQ RTN 4bit Tp8 Parameters and Internals

LLM NameHy3 GPTQ RTN 4bit Tp8
Repository 🤗https://huggingface.co/avtc/Hy3-GPTQ-RTN-4bit-tp8 
Base Model(s)  Hy3   tencent/Hy3
Model Size295b
Required VRAM161.3 GB
Updated2026-07-09
Maintaineravtc
Model Typehy_v3
Model Files  4.3 GB: 1-of-38   4.3 GB: 2-of-38   4.3 GB: 3-of-38   4.3 GB: 4-of-38   4.3 GB: 5-of-38   4.3 GB: 6-of-38   4.3 GB: 7-of-38   4.3 GB: 8-of-38   4.3 GB: 9-of-38   4.3 GB: 10-of-38   4.3 GB: 11-of-38   4.3 GB: 12-of-38   4.3 GB: 13-of-38   4.3 GB: 14-of-38   4.3 GB: 15-of-38   4.3 GB: 16-of-38   4.3 GB: 17-of-38   4.3 GB: 18-of-38   4.3 GB: 19-of-38   4.3 GB: 20-of-38   4.3 GB: 21-of-38   4.3 GB: 22-of-38   4.3 GB: 23-of-38   4.3 GB: 24-of-38   4.3 GB: 25-of-38   4.3 GB: 26-of-38   4.3 GB: 27-of-38   4.3 GB: 28-of-38   4.3 GB: 29-of-38   4.3 GB: 30-of-38   4.3 GB: 31-of-38   4.3 GB: 32-of-38   4.3 GB: 33-of-38   4.3 GB: 34-of-38   4.3 GB: 35-of-38   4.3 GB: 36-of-38   4.3 GB: 37-of-38   2.2 GB: 38-of-38
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureHYV3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.9.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<｜hy_pad:opensource｜>
Vocabulary Size120832

Best Alternatives to Hy3 GPTQ RTN 4bit Tp8

Best Alternatives
Context / RAM
Downloads
Likes
Hy3 Preview 4bit256K / 166.5 GB4062
Note: green Score (e.g. "73.2") means that the model is better than avtc/Hy3-GPTQ-RTN-4bit-tp8.

Rank the Hy3 GPTQ RTN 4bit Tp8 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? 54931 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