LLM EXPLORER 58,608 MODELS INDEXED

SuperHY3 Abliterated MLX 4bit by Jiunsong

By Jiunsong · 474 downloads
HF Repo ↗ Copy URL

SuperHY3 Abliterated MLX 4bit is an open-source language model by Jiunsong. Features: 48.1b LLM, VRAM: 169.9GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.28.

  4-bit   4bit   Abliterated   Apple-silicon Base model:jiunsong/superhy3-a... Base model:quantized:jiunsong/...   Conversational   Hunyuan   Hy3   Hy v3   Imatrix   Mlx   Moe   Obliteratus   Quantized   Region:us   Safetensors   Sharded   Supertune   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Jiunsong/SuperHY3-abliterated-MLX-4bit 

SuperHY3 Abliterated MLX 4bit Parameters and Internals

LLM NameSuperHY3 Abliterated MLX 4bit
Repository 🤗https://huggingface.co/Jiunsong/SuperHY3-abliterated-MLX-4bit 
Base Model(s)  SuperHY3 Abliterated NVFP4   Jiunsong/SuperHY3-abliterated-NVFP4
Model Size48.1b
Required VRAM169.9 GB
Updated2026-07-30
MaintainerJiunsong
Model Typehy_v3
Model Files  6.0 GB: 1-of-32   5.3 GB: 2-of-32   5.4 GB: 3-of-32   5.4 GB: 4-of-32   5.4 GB: 5-of-32   5.4 GB: 6-of-32   5.4 GB: 7-of-32   5.4 GB: 8-of-32   5.4 GB: 9-of-32   5.4 GB: 10-of-32   5.4 GB: 11-of-32   5.4 GB: 12-of-32   5.4 GB: 13-of-32   5.4 GB: 14-of-32   5.4 GB: 15-of-32   5.4 GB: 16-of-32   5.4 GB: 17-of-32   5.4 GB: 18-of-32   5.4 GB: 19-of-32   5.4 GB: 20-of-32   5.4 GB: 21-of-32   5.4 GB: 22-of-32   5.4 GB: 23-of-32   5.4 GB: 24-of-32   5.4 GB: 25-of-32   5.4 GB: 26-of-32   5.4 GB: 27-of-32   5.4 GB: 28-of-32   5.4 GB: 29-of-32   5.4 GB: 30-of-32   5.4 GB: 31-of-32   2.0 GB: 32-of-32
Quantization Type4bit
Model ArchitectureHYV3ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.6.0
Vocabulary Size120832