MoE CPU-offload benchmark on Deepseek V4/Gemma4/Qwen/GPT-OSS — TensorSharp vs llama.cpp

TensorSharp's MoE CPU-offload feature has been merged into main. Here is the parameters description of this feature: Mixture-of-Experts CPU offload: --n-cpu-moe <N> | -ncmoe <N> Keep the routed MoE expert weights of the first N layers in system RAM and multiply them on the CPU; attention, norm

中文全文翻译正在补齐，可先查看下方英文原文。

TensorSharp's MoE CPU-offload feature has been merged into main. Here is the parameters description of this feature: Mixture-of-Experts CPU offload: --n-cpu-moe <N> | -ncmoe <N> Keep the routed MoE expert weights of the first N layers in system RAM and multiply them on the CPU; attention, norm