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 OQ2 by mlx-community

 »  All LLMs  »  mlx-community  »  Hy3 OQ2   URL Share it on

  239   

Hy3 OQ2 is an open-source language model by mlx-community. Features: 29.3b LLM, VRAM: 99.1GB, Context: 256K, License: apache-2.0, LLM Explorer Score: 0.34.

  2-bit Base model:quantized:tencent/h...   Base model:tencent/hy3   Conversational   Hunyuan   Hy v3   Mlx   Moe   Oq   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Hy3-oQ2 

Hy3 OQ2 Benchmarks

LLME Score: 0.33978
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Hy3 OQ2 (mlx-community/Hy3-oQ2)
🌟 Advertise your project 🚀

Hy3 OQ2 Parameters and Internals

LLM NameHy3 OQ2
Repository 🤗https://huggingface.co/mlx-community/Hy3-oQ2 
Base Model(s)  Hy3   tencent/Hy3
Model Size29.3b
Required VRAM99.1 GB
Updated2026-07-10
Maintainermlx-community
Model Typehy_v3
Model Files  5.0 GB: 1-of-19   5.1 GB: 2-of-19   5.3 GB: 3-of-19   5.3 GB: 4-of-19   5.3 GB: 5-of-19   5.3 GB: 6-of-19   5.3 GB: 7-of-19   5.3 GB: 8-of-19   5.3 GB: 9-of-19   5.3 GB: 10-of-19   5.3 GB: 11-of-19   5.3 GB: 12-of-19   5.3 GB: 13-of-19   5.3 GB: 14-of-19   5.3 GB: 15-of-19   5.3 GB: 16-of-19   5.3 GB: 17-of-19   5.3 GB: 18-of-19   4.2 GB: 19-of-19
Model ArchitectureHYV3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.6.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<｜hy_pad:opensource｜>
Vocabulary Size120832

Rank the Hy3 OQ2 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? 54964 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