AIBao

AcceleratingLocal Intelligence.

Engineering extreme quantization for popular models likeDeepSeek, Kimi, Qwen, and more.

Local Deployment & Quantization

AIBao is a core contributor to the Moxin Organization, delivering high-fidelity GGUF quants and open-source foundations.

FoundationOpen ScienceSOTA

Moxin-7B-LLM

HF

Our flagship open-source model. SOTA performance. LLM/VLM/VLA.

1T ContextReasoningGGUF

Kimi-K2-Thinking

HF

1 Trillion Token Context. Thinking Logic. GGUF.

671BQuantizationDeepSeek

DeepSeek-V3

HF

671B Parameters. Extreme Quantization.

MoEGLMMiniMax

GLM-4.6 & MiniMax

HF

Diverse Architecture Support.

More Models...

HF

Explore our full collection of quantized models on Hugging Face.

Open Science Contributions

Fully Open Source Moxin-7B Technical Report

arXiv:2412.06845 • Dec 2024

arXiv

Ready to Deploy?

All models are available now on Hugging Face. Download the Moxin-7B series or our optimized GGUF quants today.

View the Moxin Collection
Terminal
$huggingface-cli download moxin-org/Kimi-K2-Thinking-Moxin-GGUF