STG-2000 vs Tesla T4

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the ranking	255	not rated
Place by popularity	not in top-100	not in top-100
Power efficiency	27.28	no data
Architecture	Turing (2018−2022)	no data
GPU code name	TU104	NV1
Market segment	Workstation	Desktop
Release date	13 September 2018 (7 years ago)	30 September 1995 (30 years ago)
Launch price (MSRP)	no data	$249

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores	2560	no data
Core clock speed	585 MHz	75 MHz
Boost clock speed	1590 MHz	no data
Number of transistors	13,600 million	1 million
Manufacturing process technology	12 nm	500 nm
Power consumption (TDP)	70 Watt	2 Watt
Texture fill rate	254.4	0.08
Floating-point processing power	8.141 TFLOPS	no data
ROPs	64	1
TMUs	160	1
Tensor Cores	320	no data
Ray Tracing Cores	40	no data
L1 Cache	2.5 MB	no data
L2 Cache	4 MB	no data

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface	PCIe 3.0 x16	PCI
Length	168 mm	168 mm
Width	1-slot	1-slot
Supplementary power connectors	None	None

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	GDDR6	FPM
Maximum RAM amount	16 GB	1 MB
Memory bus width	256 Bit	64 Bit
Memory clock speed	1250 MHz	50 MHz
Memory bandwidth	320.0 GB/s	400.0 MB/s

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display Connectors

No outputs

1x VGA, 1x DB13W3

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	12 Ultimate (12_1)	1.0
Shader Model	6.5	no data
OpenGL	4.6	N/A
OpenCL	1.2	N/A
Vulkan	1.2.131	N/A
CUDA	7.5	-
DLSS	+	-

Pros & cons summary

---

Recency	13 September 2018	30 September 1995
Maximum RAM amount	16 GB	1 MB
Chip lithography	12 nm	500 nm
Power consumption (TDP)	70 Watt	2 Watt

Vote for your favorite

Do you think we are right or mistaken in our choice? Vote by clicking "Like" button near your favorite graphics card.

---