面壁智能 MiniCPM-o 4.5 现可通过 TyloQuant MFQ 量化版在 Apple Silicon 上高效运行，支持本地多模态推理。TyloQuant MFQ 采用神经元感知的混合格式量化，在降低内存占用的同时保留视觉、音频与实时交互能力，并提供多种量化等级及 Metal/CUDA 内核加速。
MiniCPM-o 4.5 now runs efficiently on Apple Silicon with TyloQuant MFQ! 🥰
The team at @Tylogi_ai has released an MFQ-quantized build of MiniCPM-o 4.5, bringing efficient multimodal inference to local devices.
Rather than applying a single quantization format uniformly, TyloQuant MFQ uses neuron-aware mixed-format quantization to reduce memory usage while retaining MiniCPM-o 4.5’s vision, audio, and real-time interaction capabilities. 🤖
Highlights:
⚡ Native acceleration with Metal on Apple Silicon
📉 Multiple quantization levels for different memory and quality targets
🎥 Vision, audio, and full-duplex multimodal interaction
🛠️ MFQ-backed Metal and CUDA kernels with native C++ runtime components
This release shows how advanced mixed-format quantization can make powerful multimodal models more practical for private, local, and edge deployment.
🤖 MiniCPM-o 4.5 model:
http://huggingface.co/openbmb/MiniCPM-o-4_5
🔗 Explore the MFQ model:
http://github.com/Tylogi/TyloQuant
📦 Download the MFQ model:
http://www.modelscope.cn/models/Tylogi/MiniCPM-o-4_5-MFQ
来源：OpenBMB · x.com