GeekRadar / The comparison desk

COMPARE.

GPU

NVIDIA

NVIDIA Jetson T4000

Graphics processor

Video memory: 64 GB^*
Memory bus: 256 bit^*
Rated memory bandwidth: 273.20 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Blackwell^*
Process node: 3 nm^*
GPU cores: 1,536^*
Graphics interface: PCIe 5.0 x16^*
GPU L2 cache: 50 MB^*
Graphics processor: GB10B^*
Texture mapping units: 64^*
Raster output units: 16^*
Streaming multiprocessors: 12^*
Tensor cores: 64^*
Ray tracing cores: 12^*
Chip foundry: TSMC^*
Card or module format: IGP^*
Declared GPU TDP: 40 W^*
Suggested system PSU: 200 W^*
External power connectors: None^*
OpenCL: 3.0^*
CUDA compute capability: 11.0^*

Memory & storage

Memory options: 64^*
Video memory: 64 GB^*
Video memory type: LPDDR5X^*
Memory bus: 256 bit^*
Rated memory bandwidth: 273.20 GB/s^*

Power specifications

Thermal design power: 40 W^*

System configuration

Detailed specifications

Specifications 1 · 28 fields

cores: 1,536^*
tensor cores: 64^*
rt cores: 12^*
sm count: 12^*
base clock: 1,665^*
boost clock: 2,525^*
memory clock: 1,067^*
ram: 64^*
name: NVIDIA Jetson T4000^*
ram type: LPDDR5X^*
bus width: 256^*
bus interface: PCIe 5.0 x16^*
ram bandwidth: 273.2^* GB/s
fp16 performance: 31.03^*
fp32 performance: 7.757^*
fp64 performance: 3.878^*
tdp: 40^* W
suggested psu: 200^* W
slot width: IGP^*
api cuda: 11^*
is retail board: No^*
gpi value: 7.48^*
vendor: nvd^*
manufacturer: NVIDIA^*
arch name: Blackwell^*
card release date: 2025-08-27^*
proc foundry: TSMC^*
proc process size: 3^* nm

Specifications 2 · 34 fields

CUDA compute capability

11.0^*

OpenCL

3.0^*

Architecture

Blackwell^*

Graphics interface

PCIe 5.0 x16^*

Memory bus

256^* bit

Reported shader processors

1,536^*

Reported theoretical FP16 peak

31.03^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP32 peak

7.757^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Reported theoretical FP64 peak

3.878^* TFLOPS

Scope and conditions

Arithmetic density: Not stated^*

Declared L1 cache configuration

256 KB (per SM)^*

Declared GPU L2 cache

50 MB^*

Reported display outputs

1x HDMI^*

Theoretical pixel fill rate

40.40 GPixel/s^*

External power connectors

None^*

Chip foundry

TSMC^*

Process node declaration

3 nm^*

Graphics processor

GB10B^*

Reported video memory

64^* GB

Rated memory bandwidth

273.2 GB/s^*

Video memory type

LPDDR5X^*

Raster output units

16^*

Ray tracing cores

12^*

Reported shading units

1,536^*

Card or module format

IGP^*

Streaming multiprocessors

12^*

Suggested system PSU

200 W^*

2:4 tensor sparsity

Yes^*

Declared GPU TDP

40 W^*

Tensor cores

64^*

Theoretical texture fill rate

161.6 GTexel/s^*

Texture mapping units

64^*

GPU cores

1,536^*

Video memory

64^* GB

Video memory type

LPDDR5X^*

* Provisional data