Downloads · 30 days
0
CPU-Hybrid-MoE/DeepSeek-R1-0528-CPU-NUMA2-AMXINT4
DeepSeek-R1-0528-CPU-NUMA2-AMXINT4 is a text generation model from CPU-Hybrid-MoE. Use it when you need the model to write or continue text.
Mirrored from https://modelscope.cn/models/ApproachingAI2024/DeepSeek-R1-0528-CPU-weight
Downloads · 30 days
0
Access
Public
Updated Oct 25, 2025
Repo size
328 GB
Likes
0
Public
Click a slice to open those files.
.safetensors328 GB · 100%
From the Hugging Face model README
Mirrored from https://modelscope.cn/models/ApproachingAI2024/DeepSeek-R1-0528-CPU-weight
For inference with sglang and kt-kernel: https://lmsys.org/blog/2025-10-22-KTransformers/
This version is packed specifically for NUMA tensor parallel = 2