GPUEmbeddedReleased —

NVIDIA RTX A1000 Embedded

128-bit · 2,048 cores

The RTX A1000 Embedded is a professional MXM 3.1 Type A graphics module (82 x 70 mm) for industrial, medical, transport and edge AI systems. NVIDIA partners such as ADLINK first offered modules based on it from November 2021, with five-year long-life availability for embedded design-ins, and the same GPU configuration is also sold as the RTX A1000 laptop GPU. It drives up to four DisplayPort 1.4 outputs at up to 7680 x 4320 resolution.

General

Manufacturer: NVIDIA
Model: RTX A1000 Embedded
Segment: Embedded
GPU chip: GA107
Architecture: Ampere
Release date: —
Price: Search on Amazon

Memory

Memory size: 4 GB
Memory type: GDDR6
Bus width: 128-bit
Bandwidth: 224 GB/s
Memory clock: 1,750 MHz

Clocks & silicon

GPU clock: —
Boost clock: 1,627 MHz
Shader units: 2,048 CUDA Cores
Tensor / AI cores: 64
RT cores: 16
Transistors: 8.7 billion
Technology (nm): 8 nm
Samsung 8 nm (8N)
TDP / TBP: 60 W

Interface & APIs

Bus interface: MXM 3.1 Type A (PCIe 4.0 x8)
SLI / multi-GPU: —
DirectX: 12 Ultimate (12_2)
OpenGL: 4.6
Vulkan: 1.3
Other APIs: CUDA 8.6, OpenCL 3.0, NVENC (H.264/HEVC), NVDEC (H.264/HEVC/AV1)

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: 64 3rd-gen Tensor Cores + 16 2nd-gen RT Cores
Peak AI TOPS: —
Notes: Third-generation Tensor Cores support TF32, FP16, BF16, INT8 and INT4 with structural sparsity; FP8 is not available on Ampere. NVIDIA publishes 6.66 TFLOPS FP32 at the 60 W Type A configuration but no Tensor TOPS figure for this module. Bandwidth of 224 GB/s follows NVIDIA's embedded specification table (14 Gbps GDDR6); some partner datasheets quote 192 GB/s for lower-power variants.

All NVIDIA GPUs →

Embedded gpus from NVIDIA announced around the same time as the NVIDIA RTX A1000 Embedded. Add any of them to your compare list to see the specs side by side.

gpu