Experimental only. No DeepSeek Sparse Attention supported by llama.cpp currently. So using regular attention from Deepseek V3.1

Should be working with main branch from llama.cpp.

Downloads last month
18
GGUF
Model size
671B params
Architecture
deepseek2
Hardware compatibility
Log In to add your hardware

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lovedheart/DeepSeek-V3.2-GGUF-Experimental

Quantized
(24)
this model