Tesla K20c vs Quadro RTX 4000

Place in the ranking	107	487
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	36.09	0.35
Power efficiency	17.30	2.76
Architecture	Turing (2018−2022)	Kepler (2012−2018)
GPU code name	TU104	GK110
Market segment	Workstation	Workstation
Release date	13 November 2018 (6 years ago)	12 November 2012 (12 years ago)
Launch price (MSRP)	$899	$3,199

Cost-effectiveness evaluation

Performance to price ratio. The higher, the better.

RTX 4000 has 10211% better value for money than Tesla K20c.

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	2304	2496
Core clock speed	1005 MHz	706 MHz
Boost clock speed	1545 MHz	no data
Number of transistors	13,600 million	7,080 million
Manufacturing process technology	12 nm	28 nm
Power consumption (TDP)	160 Watt	225 Watt
Texture fill rate	222.5	146.8
Floating-point processing power	7.119 TFLOPS	3.524 TFLOPS
ROPs	64	40
TMUs	144	208
Tensor Cores	288	no data
Ray Tracing Cores	36	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	PCIe 2.0 x16
Length	241 mm	267 mm
Width	1-slot	2-slot
Supplementary power connectors	1x 8-pin	1x 6-pin + 1x 8-pin

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	GDDR5
Maximum RAM amount	8 GB	5 GB
Memory bus width	256 Bit	320 Bit
Memory clock speed	1625 MHz	1300 MHz
Memory bandwidth	416.0 GB/s	208.0 GB/s

Connectivity and outputs

Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.

Display Connectors

3x DisplayPort, 1x USB Type-C

No outputs

API compatibility

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

DirectX	12 Ultimate (12_1)	12 (11_0)
Shader Model	6.5	5.1
OpenGL	4.6	4.6
OpenCL	1.2	1.2
Vulkan	1.2.131	1.1.126
CUDA	7.5	3.5

Gaming performance

Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.

Pros & cons summary

Performance score	39.72	8.90
Recency	13 November 2018	12 November 2012
Maximum RAM amount	8 GB	5 GB
Chip lithography	12 nm	28 nm
Power consumption (TDP)	160 Watt	225 Watt

RTX 4000 has a 346.3% higher aggregate performance score, an age advantage of 6 years, a 60% higher maximum VRAM amount, a 133.3% more advanced lithography process, and 40.6% lower power consumption.

The Quadro RTX 4000 is our recommended choice as it beats the Tesla K20c in performance tests.

Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.