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 Preview 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Hy3 Preview 4bit   URL Share it on

  428   

Hy3 Preview 4bit is an open-source language model by mlx-community. Features: 295b LLM, VRAM: 166.5GB, Context: 256K, License: other, Quantized, LLM Explorer Score: 0.44, ELO: 1418.

  4-bit   4bit Base model:quantized:tencent/h...   Base model:tencent/hy3-preview   Conversational   Hy v3   Mlx   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Hy3-preview-4bit 

Hy3 Preview 4bit Benchmarks

LMSys ELO: 1418 vs 1272 (so35)11.5%
LLME Score: 0.44305
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hy3 Preview 4bit (mlx-community/Hy3-preview-4bit)
🌟 Advertise your project 🚀

Hy3 Preview 4bit Parameters and Internals

LLM NameHy3 Preview 4bit
Repository 🤗https://huggingface.co/mlx-community/Hy3-preview-4bit 
Base Model(s)  Hy3 Preview   tencent/Hy3-preview
Model Size295b
Required VRAM166.5 GB
Updated2026-05-11
Maintainermlx-community
Model Typehy_v3
Model Files  5.3 GB: 1-of-34   4.9 GB: 2-of-34   4.9 GB: 3-of-34   4.9 GB: 4-of-34   4.9 GB: 5-of-34   4.9 GB: 6-of-34   4.9 GB: 7-of-34   4.9 GB: 8-of-34   4.9 GB: 9-of-34   4.9 GB: 10-of-34   4.9 GB: 11-of-34   4.9 GB: 12-of-34   4.9 GB: 13-of-34   4.9 GB: 14-of-34   4.9 GB: 15-of-34   4.9 GB: 16-of-34   4.9 GB: 17-of-34   4.9 GB: 18-of-34   4.9 GB: 19-of-34   4.9 GB: 20-of-34   4.9 GB: 21-of-34   4.9 GB: 22-of-34   4.9 GB: 23-of-34   4.9 GB: 24-of-34   4.9 GB: 25-of-34   4.9 GB: 26-of-34   4.9 GB: 27-of-34   4.9 GB: 28-of-34   4.9 GB: 29-of-34   4.9 GB: 30-of-34   4.9 GB: 31-of-34   4.9 GB: 32-of-34   4.9 GB: 33-of-34   4.4 GB: 34-of-34
Quantization Type4bit
Model ArchitectureHYV3ForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version5.6.0
Tokenizer ClassTokenizersBackend
Padding Token<｜hy_▁pad▁｜>
Vocabulary Size120832

Rank the Hy3 Preview 4bit 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? 53640 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