DeepSeek-V4-Flash in MXFP4 is too slow on CPU
英文标题：DeepSeek-V4-Flash in MXFP4 is too slow on CPU
I have an old Xeon rig with 512Gb of 4-channel DDR4 2133 memory and E5-2699v4 processor. For GPU I have GTX 1060 with 6Gb of VRAM, so I use CPU only mode. I can run GLM 5.2 with 40B active parameters in Q4_K_XL at 1.8 t/s, but as you can understand it is too slow. So I wanted to give a try to a new
打开原文相关 2 · 机会 0
中文
I have an old Xeon rig with 512Gb of 4-channel DDR4 2133 memory and E5-2699v4 processor. For GPU I have GTX 1060 with 6Gb of VRAM, so I use CPU only mode. I can run GLM 5.2 with 40B active parameters in Q4_K_XL at 1.8 t/s, but as you can understand it is too slow. So I wanted to give a try to a new
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
I have an old Xeon rig with 512Gb of 4-channel DDR4 2133 memory and E5-2699v4 processor. For GPU I have GTX 1060 with 6Gb of VRAM, so I use CPU only mode. I can run GLM 5.2 with 40B active parameters in Q4_K_XL at 1.8 t/s, but as you can understand it is too slow. So I wanted to give a try to a new