NVIDIA T4

URI: https://gptkb.org/entity/NVIDIA_T4

GPTKB entity

Predicate	Object
gptkbp:instanceOf	gptkb:graphics_card
gptkbp:architecture	gptkb:Turing
gptkbp:coreCount	2560
gptkbp:formFactor	low-profile
https://www.w3.org/2000/01/rdf-schema#label	NVIDIA T4
gptkbp:interface	PCIe 3.0 x16
gptkbp:manufacturer	gptkb:NVIDIA
gptkbp:maximumSpeed	70 W
gptkbp:memoryBusWidth	320 GB/s
gptkbp:memoryType	gptkb:GDDR6
gptkbp:passivelyCooled	true
gptkbp:predecessor	NVIDIA P4
gptkbp:processNode	12 nm FinFET
gptkbp:RAM	16 GB
gptkbp:releaseDate	September 2018
gptkbp:RT_Cores	40
gptkbp:singleSlot	true
gptkbp:successor	gptkb:NVIDIA_A10
gptkbp:supports	gptkb:CUDA gptkb:TensorRT gptkb:PCIe_Gen3 gptkb:NVIDIA_GPU_Cloud gptkb:NVIDIA_NVDEC gptkb:NVIDIA_NVENC virtualization FP16 INT4 INT8 FP32 video transcoding Deep Learning frameworks multi-precision computing
gptkbp:targetMarket	gptkb:cloud_service gptkb:machine_learning cloud computing AI inference
gptkbp:TDP	70 W
gptkbp:Tensor_Cores	320
gptkbp:transistorCount	13.6 billion
gptkbp:bfsParent	gptkb:NVIDIA_EGX gptkb:NVIDIA_DeepStream gptkb:NVIDIA_EGX_platform gptkb:Tensor_Cores
gptkbp:bfsLayer	7