CPU-Hybrid-MoE

community

AI & ML interests

Quantized MoE models for inference on CPU and hybrid CPU-GPU

Recent Activity

Doctor-Shotgun updated a model about 1 month ago

CPU-Hybrid-MoE/DeepSeek-R1-0528-GPU-FP8-GPTQ4

Doctor-Shotgun updated a model about 1 month ago

CPU-Hybrid-MoE/DeepSeek-V3-0324-GPU-FP8-GPTQ4

Doctor-Shotgun published a model 2 months ago

CPU-Hybrid-MoE/DeepSeek-R1-0528-GPU-FP8-GPTQ4

View all activity

models 8

CPU-Hybrid-MoE/DeepSeek-R1-0528-GPU-FP8-GPTQ4

Text Generation • 106B • Updated Nov 12 • 7

CPU-Hybrid-MoE/DeepSeek-V3-0324-GPU-FP8-GPTQ4

Text Generation • 106B • Updated Nov 12 • 14

CPU-Hybrid-MoE/DeepSeek-V3-0324-CPU-NUMA4-AMXINT8

Text Generation • Updated Oct 26 • 8

CPU-Hybrid-MoE/DeepSeek-V3-0324-CPU-NUMA4-AMXINT4

Text Generation • Updated Oct 26 • 11

CPU-Hybrid-MoE/DeepSeek-R1-0528-CPU-NUMA2-AMXINT4

Text Generation • Updated Oct 25

CPU-Hybrid-MoE/DeepSeek-V3-0324-CPU-NUMA2-AMXINT4

Text Generation • Updated Oct 24

CPU-Hybrid-MoE/GLM-4.5V-GPU-weight

Image-Text-to-Text • 33B • Updated Oct 24 • 8

CPU-Hybrid-MoE/GLM-4.5-Air-GPU-weight

32B • Updated Oct 24 • 4

datasets 0

None public yet