ProductNVIDIA® A10 GPU Computing Accelerator - 24GB GDDR6 - PCIe 4.0 x16 - Passive Cooler (w/o CEC)NVIDIA® A16 GPU Computing Accelerator - 64GB (4x 16GB) GDDR6 - PCIe 4.0 x16 - Passive Cooler (w/o CEC)NVIDIA® L4 ADA GPU Computing Accelerator - 24GB GDDR6X - PCIe 4.0 x16 - Passive CoolingNVIDIA® L40 ADA GPU Computing Accelerator - 48GB GDDR6 - PCIe 4.0 x16 - Passive CoolingNVIDIA® L40S ADA GPU Computing Accelerator - 48GB GDDR6 - PCIe 4.0 x16 - Passive CoolingNVIDIA® H100 NVL GPU Computing Accelerator - 94GB HBM3 - PCIe 5.0 x16 - Passive CoolingNVIDIA® H200 NVL GPU Computing Accelerator - 141GB HBM3e - PCIe 5.0 x16 - Passive CoolingNVIDIA® RTX PRO 6000 Blackwell Server Edition - 96GB GDDR7 ECC - PCIe 5.0 x16 - Passive Cooling (4xDP)
ActionSelectSelectSelectSelectSelectSelectSelectSelect
Main Specifications
Product Series Nvidia A10Nvidia A16Nvidia L4Nvidia L40Nvidia L40SNvidia H100 NVLNvidia H200
Core Type NVIDIA TENSORNVIDIA TENSORNVIDIA TENSORNVIDIA TENSORNVIDIA TENSORNVIDIA TENSORNVIDIA TENSOR
Core Clock Speed 885 MHz (1695 MHz Boost Clock)795 MHz Base | 2040 MHz Boost
Host Interface PCI Express 4.0 x16 64GB/sPCI Express 4.0 x16PCI Express 4.0 x16PCI Express 4.0 x16PCI Express 4.0 x16PCI Express 5.0 x16PCI Express 5.0 x16PCI Express 5.0 x16
GPU Architecture AmpereAmpereAda LovelaceAda LovelaceAda LovelaceHopperHopper
Product Type Server
Product Line NVIDIA Professional Graphics
Memory Technology GDDR7
Memory Capacity 96 GB with ECC
Max Displays 4 Displays
Detailed Specifications
Streaming Processor Cores 18,17624,064 CUDA Parallel Processing Cores
NVIDIA Tensor Cores 568 | Gen 4752 (5th Gen)
NVIDIA RT Cores 72 RT Cores142 | Gen 3188 (4th Gen)
PCIe x16 Interconnect Bandwidth PCIe Gen5: 128GB/s
Memory Clock Speed 1563 MHz6251 MHz
Memory Interface 192-bit512-bit
Max Memory Size 24 GB GDDR64x 16GB GDDR6 with error-correcting code (ECC)24 GB48 GB GDDR6 with ECC48GB GDDR6 with ECC94 GB141 GB
Max Memory Bandwidth 600 GB/s4x 232GB/s300 GB/s864 GB/s7.8TB/s4.8TB/s
ECC Protection On by Default
Peak FP64 68 teraFLOPs30 TFLOPS
Peak FP64 Tensor Core 134 teraFLOPs60 TFLOPS
INT8 Tensor Core 250 TOPS | 500 TOPS485 TOPS | Sparsity733 teraFLOPS7,916 TOPS3,341 TFLOPS
TF32 Tensor Core 62.5 teraFLOPS | 125 teraFLOPS120 TFLOPS | Sparsity183 teraFLOPS1,979 teraFLOPs835 TFLOPS
FP32 31.2 teraFLOPS30.3 TFLOPS91.6 teraFLOPS134 teraFLOPs60 TFLOPS
Peak BFLOAT16 Tensor Core 125 teraFLOPS | 250 teraFLOPS242 TFLOPS | Sparsity362.05 teraFLOPS3,958 teraFLOPs1,671 TFLOPS
Peak FP16 Tensor Core 125 teraFLOPS | 250 teraFLOPS242 TFLOPS | Sparsity362.05 teraFLOPS3,958 teraFLOPs1,671 TFLOPS
Peak FP8 Tensor Core 485 TFLOPS | Sparsity733 teraFLOPS7,916 teraFLOPs3,341 TFLOPS
Peak INT4 Tensor Core 500 TOPS | 1,000 TOPS733 teraFLOPS
Total NVLink Bandwidth Not supported600GB/s
Multi-Instance GPUs No
vGPU Software Support NVIDIA vPC/vApps, NVIDIA RTX Virtual Workstation (vWS)
NVENC | NVDEC 2 | 4 | 4 | JPEG Decoders | AV1 Encode and Decode3x | 3x (Includes AV1 Encode & Decode)3x l 3x (includes AV1 encode and decode)
Secure Boot with Root of Trust YesYesYes
NEBS Ready Yes | Level 3Yes / Level 3Level 3
DisplayPort Connectors None | vGPU Only4x DP 1.4a4x DisplayPort 1.4a
Cooling PassivePassivePassivePassivePassivePassivePassive
Dual Slot Single-slotDual-slotNoYesYes
Dimensions FHFL4.4" (H) x 10.5" (L)4.4" (H) x 10.5" (L)4.4” H x 10.5” L, FHFL Dual Slot
Form Factor 6.61” L x 2.71” H (Low-profile)PCIePCIeDual-slot air-cooled
Lithography 8 nm4N NVIDIA Custom Process
Supplementary Power Connectors None8-pin CPU1x 16-pin PCIe CEM51x 16-pin1x PCIe CEM5 16-pin
Max Graphics Card Power (W) 150W250W72W300W350W400WUp to 600W (configurable)400 W – 600 W (configurable)
Processor NVIDIA Blackwell Architecture
Memory Bandwidth Up to 1.6 TB/s
Minimum Recommended Power, Single Card (W) 800
Minimum Recommended Power, 2-Way (W) 1600
Minimum Recommended Power, 3-Way (W) 2000
Minimum Recommended Power, 4-Way (W) 2400
Thermal Solution Passive
Slot Height 2-Slot
ActionSelectSelectSelectSelectSelectSelectSelectSelect