Quantized MTP head of Deepseek R1. For use with the Unsloth's Q4_K quants.

Llama.cpp does not support MTP heads, but vLLM does.

Downloads last month
14
GGUF
Model size
12.5B params
Architecture
llama
Hardware compatibility
Log In to view the estimation
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for pdelobelle/DeepSeek-R1-GGUF-MTP

Quantized
(55)
this model