GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →

jackasda211233 author hub

Tencent Hy3 HunYuan 3 — IQ4 NL GGUF 295B parameter Mixture of Experts model quantized to IQ4 NL 4.5 bits per weight , 158 GB. ⚠️ Requires a Custom Fork of ik llama This model will not load on standard llama.cpp or standard ik llama.cpp. It requires a fork with hy v3 architecture…

Models
4
Downloads
3,309
jackasda211233/Hy3-IQ4_NL-GGUF
0 downloads · text-generation

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models