Downloads · 30 days
93
37% of all-time downloads
CPU-Hybrid-MoE/DeepSeek-V3-0324-GPU-FP8-GPTQ4
DeepSeek-V3-0324-GPU-FP8-GPTQ4 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-V3-0324-GPU-weight
Downloads · 30 days
93
37% of all-time downloads
All-time downloads
251
Public
Parameters
678B
360 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors360 GB · 100%
How the weights are stored.
I32654B · 96%
From the Hugging Face model README
Mirrored from https://modelscope.cn/models/ApproachingAI2024/DeepSeek-V3-0324-GPU-weight
For inference with sglang and kt-kernel: https://lmsys.org/blog/2025-10-22-KTransformers/