GPUWorkstationReleased May 6, 2021

NVIDIA T1000

8 GB GDDR6 · 128-bit · 896 cores

The NVIDIA T1000 is a low-profile, single-slot workstation card from NVIDIA's 2021 small-form-factor Turing lineup, alongside the T600 and T400. It draws at most 50 W with no auxiliary power connector and has four latching mini DisplayPort 1.4 outputs that can drive four 5K displays or two 8K displays. It was first offered with 4 GB of GDDR6, and a T1000 8GB version followed.

General

Manufacturer: NVIDIA
Model: T1000
Segment: Workstation
GPU chip: TU117
Architecture: Turing
Release date: May 6, 2021
Price: Search on Amazon

Memory

Memory size: 4 – 8 GB
Memory type: GDDR6
Bus width: 128-bit
Bandwidth: 160 GB/s
Memory clock: 1,250 MHz

Clocks & silicon

GPU clock: 1,065 MHz
Boost clock: 1,395 MHz
Shader units: 896 CUDA Cores
Tensor / AI cores: —
RT cores: —
Transistors: 4.7 billion
Technology (nm): 12 nm
TSMC 12 nm FFN
TDP / TBP: 50 W

Interface & APIs

Bus interface: PCIe 3.0 x16
SLI / multi-GPU: —
DirectX: 12.0 (Shader Model 5.1)
OpenGL: 4.6
Vulkan: 1.4
Other APIs: CUDA 7.5, DirectCompute, OpenCL

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: None (no Tensor Cores)
Peak AI TOPS: —
Notes: TU117 has no Tensor Cores. The CUDA cores run FP16 at twice the FP32 rate and support INT8 dot-product instructions; NVIDIA rates the card at up to 2.5 TFLOPS FP32.