ModelNVIDIA RTX A1000

Memory8GB GDDR6, 128bit, 12Gbps, 1500MHz, 192GB/​s

clock Base727MHz

clock Boost1462MHz

overclock-

Cooling1x radial-fan (40mm)

TDP/TGP50W (NVIDIA)

AI-Computing powernot available

GPU-Computing power6.74 TFLOPS (FP16), 6.74 TFLOPS (FP32), 0.11 TFLOPS (FP64)

Power connections-

Connectors4x mini DisplayPort 1.4a

InterfacePCIe 4.0 x16 (x8)

Special featuresNVIDIA-reference design, without LHR (Lite Hash Rate), 4x mDP-DP adapter

total heightSingle Slot

Dimensions162.56x68.58mm (LxW)

TypePCIe card (low profile)

PCI slot bracketlow profile + full height (product content)

Chip-data

Chip-ArchitectureAmpere (from 2020/​Q3)

Chip-titleGA107

Chip-Configuration18SM (2304SP /​ 72TMU /​ 32ROP), 18 RT Cores, 72 Tensor Cores, 2MiB L2 cache

Chip-Manufacturing ProcessSamsung 8nm

Chip size200mm², monolithisch, 8.7 Mrd. Transistoren

Chip-functionsRaytracing (2nd Gen NVIDIA RTX), NVIDIA Tensor (3rd Gen), 10bit colour channel depth, HDCP 2.3

API-supportDirectX 12 Ultimate (12_2) /​ CUDA 8.6 /​ Vulkan 1.3 /​ OpenCL 3.0 /​ OpenGL 4.6 /​ Shader Model 6.7

Transcoding-Engine1x NVENC (7th Gen, max. Sessions: 8), 2x NVDEC (5th Gen), Info

encodingH.265 (4K YUV 4:2:0 /​ 4K YUV 4:4:4 /​ 4K Lossless /​ 8K /​ HEVC 10bit support), H.264 (YUV 4:2:0 /​ YUV 4:4:4 /​ Lossless)

decodingAV1 (8bit /​ 10bit), H.265 (8bit 4:2:0 /​ 10bit 4:2:0 /​ 12bit 4:2:0 /​ 8bit 4:4:4 /​ 10bit 4:4:4 /​ 12bit 4:4:4), H.264, VP9 (8bit /​ 10bit /​ 12bit), VP8, VC-1, MPEG-2, MPEG-1

Multi-GPU-Interface-

Vorstellung (series)16.04.2024

GraphicsNVIDIA RTX A1000 - 8GB GDDR6 - desktop