L20 vs Tesla M2070

Place in the ranking	698	189
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	0.05	no data
Power efficiency	1.54	8.97
Architecture	Fermi (2010−2014)	Ada Lovelace (2022−2024)
GPU code name	GF100	AD102
Market segment	Workstation	Workstation
Release date	25 July 2011 (14 years ago)	16 November 2023 (2 years ago)
Launch price (MSRP)	$3,099	no data

Cost-effectiveness evaluation

The higher the ratio, the better. We use the manufacturer's recommended prices.

no data

Performance to price scatter graph

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	448	11776
Core clock speed	574 MHz	1440 MHz
Boost clock speed	no data	2520 MHz
Number of transistors	3,100 million	76,300 million
Manufacturing process technology	40 nm	5 nm
Power consumption (TDP)	225 Watt	275 Watt
Texture fill rate	32.14	927.4
Floating-point processing power	1.03 TFLOPS	59.35 TFLOPS
ROPs	48	128
TMUs	56	368
Tensor Cores	no data	368
Ray Tracing Cores	no data	92
L1 Cache	896 KB	11.5 MB
L2 Cache	768 KB	96 MB

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 2.0 x16	PCIe 4.0 x16
Length	248 mm	267 mm
Width	2-slot	2-slot
Supplementary power connectors	1x 6-pin + 1x 8-pin	1x 16-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	GDDR5	GDDR6
Maximum RAM amount	6 GB	48 GB
Memory bus width	384 Bit	384 Bit
Memory clock speed	783 MHz	2250 MHz
Memory bandwidth	150.3 GB/s	864.0 GB/s
Resizable BAR	-	+

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

4x DisplayPort 1.4a

API and SDK support

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

DirectX	12 (11_0)	12 Ultimate (12_2)
Shader Model	5.1	6.7
OpenGL	4.6	4.6
OpenCL	1.1	3.0
Vulkan	N/A	1.3
CUDA	2.0	8.9
DLSS	-	+

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	4.47	31.82
Recency	25 July 2011	16 November 2023
Maximum RAM amount	6 GB	48 GB
Chip lithography	40 nm	5 nm
Power consumption (TDP)	225 Watt	275 Watt

Tesla M2070 has 22.2% lower power consumption.

L20, on the other hand, has a 611.9% higher aggregate performance score, an age advantage of 12 years, a 700% higher maximum VRAM amount, and a 700% more advanced lithography process.

The L20 is our recommended choice as it beats the Tesla M2070 in performance tests.