L40S vs GeForce RTX 3080 Ti

Place in the ranking	22	67
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	22.73	no data
Power efficiency	13.85	11.29
Architecture	Ampere (2020−2024)	Ada Lovelace (2022−2024)
GPU code name	GA102	AD102
Market segment	Desktop	Workstation
Release date	31 May 2021 (3 years ago)	13 October 2022 (2 years ago)
Launch price (MSRP)	$1,199	no data

Cost-effectiveness evaluation

The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.

no data

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	10240	18176
Core clock speed	1365 MHz	1110 MHz
Boost clock speed	1665 MHz	2520 MHz
Number of transistors	28,300 million	76,300 million
Manufacturing process technology	8 nm	5 nm
Power consumption (TDP)	350 Watt	300 Watt
Texture fill rate	532.8	1,431
Floating-point processing power	34.1 TFLOPS	91.61 TFLOPS
ROPs	112	192
TMUs	320	568
Tensor Cores	320	568
Ray Tracing Cores	80	142

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 4.0 x16	PCIe 4.0 x16
Length	285 mm	267 mm
Width	2-slot	2-slot
Supplementary power connectors	1x 12-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	GDDR6X	GDDR6
Maximum RAM amount	12 GB	48 GB
Memory bus width	384 Bit	384 Bit
Memory clock speed	1188 MHz	2250 MHz
Memory bandwidth	912.4 GB/s	864.0 GB/s
Shared memory	-	-

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	1x HDMI, 3x DisplayPort	1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI	+	+

API and SDK compatibility

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

DirectX	12 Ultimate (12_2)	12 Ultimate (12_2)
Shader Model	6.6	6.7
OpenGL	4.6	4.6
OpenCL	3.0	3.0
Vulkan	1.2	1.3
CUDA	8.6	8.9

Synthetic benchmark performance

Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.

Combined synthetic benchmark score

This is our combined benchmark score. We are regularly improving our combining algorithms, but if you find some perceived inconsistencies, feel free to speak up in comments section, we usually fix problems quickly.

RTX 3080 Ti 68.23
+43.1%

L40S 47.67

Passmark

This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.

RTX 3080 Ti 27022
+43.1%

L40S 18881

GeekBench 5 OpenCL

Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses OpenCL API by Khronos Group.

RTX 3080 Ti 209081

L40S 346825
+65.9%

Gaming performance

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

Average FPS across all PC games

Here are the average frames per second in a large set of popular games across different resolutions:

Full HD	214 +52.9%	140−150 −52.9%
1440p	146 +46%	100−110 −46%
4K	98 +50.8%	65−70 −50.8%

Cost per frame, $

1080p	5.60	no data
1440p	8.21	no data
4K	12.23	no data

FPS performance in popular games

Full HD
Low Preset

Counter-Strike 2	160−170 +50%	110−120 −50%
Cyberpunk 2077	219 +46%	150−160 −46%

Full HD
Medium Preset

Battlefield 5	110−120 +46.3%	80−85 −46.3%
Counter-Strike 2	160−170 +50%	110−120 −50%
Cyberpunk 2077	92 +53.3%	60−65 −53.3%
Forza Horizon 4	489 +63%	300−310 −63%
Forza Horizon 5	220 +46.7%	150−160 −46.7%
Metro Exodus	174 +45%	120−130 −45%
Red Dead Redemption 2	120−130 +50.6%	85−90 −50.6%
Valorant	350−400 +48.8%	240−250 −48.8%

Full HD
High Preset

Battlefield 5	110−120 +46.3%	80−85 −46.3%
Counter-Strike 2	160−170 +50%	110−120 −50%
Cyberpunk 2077	80 +45.5%	55−60 −45.5%
Dota 2	194 +49.2%	130−140 −49.2%
Far Cry 5	140 +47.4%	95−100 −47.4%
Fortnite	270−280 +45.8%	190−200 −45.8%
Forza Horizon 4	407 +45.4%	280−290 −45.4%
Forza Horizon 5	180−190 +51.7%	120−130 −51.7%
Grand Theft Auto V	174 +45%	120−130 −45%
Metro Exodus	151 +51%	100−105 −51%
PLAYERUNKNOWN'S BATTLEGROUNDS	210−220 +43.3%	150−160 −43.3%
Red Dead Redemption 2	56 +60%	35−40 −60%
The Witcher 3: Wild Hunt	170−180 +45%	120−130 −45%
Valorant	350−400 +48.8%	240−250 −48.8%
World of Tanks	270−280 +46.8%	190−200 −46.8%

Full HD
Ultra Preset

Battlefield 5	110−120 +46.3%	80−85 −46.3%
Counter-Strike 2	160−170 +50%	110−120 −50%
Cyberpunk 2077	136 +43.2%	95−100 −43.2%
Dota 2	217 +44.7%	150−160 −44.7%
Far Cry 5	130−140 +46.7%	90−95 −46.7%
Forza Horizon 4	359 +43.6%	250−260 −43.6%
Forza Horizon 5	176 +46.7%	120−130 −46.7%
PLAYERUNKNOWN'S BATTLEGROUNDS	210−220 +43.3%	150−160 −43.3%
Valorant	388 +43.7%	270−280 −43.7%

1440p
High Preset

Counter-Strike 2	40−45 +51.9%	27−30 −51.9%
Dota 2	153 +53%	100−105 −53%
Grand Theft Auto V	153 +53%	100−105 −53%
PLAYERUNKNOWN'S BATTLEGROUNDS	170−180 +45.8%	120−130 −45.8%
Red Dead Redemption 2	93 +55%	60−65 −55%
World of Tanks	500−550 +66.7%	300−310 −66.7%

1440p
Ultra Preset

Battlefield 5	85−90 +45%	60−65 −45%
Cyberpunk 2077	92 +53.3%	60−65 −53.3%
Far Cry 5	160−170 +45.5%	110−120 −45.5%
Forza Horizon 4	269 +49.4%	180−190 −49.4%
Forza Horizon 5	130−140 +50%	90−95 −50%
Metro Exodus	141 +48.4%	95−100 −48.4%
The Witcher 3: Wild Hunt	150−160 +56%	100−105 −56%
Valorant	316 +43.6%	220−230 −43.6%

4K
High Preset

Counter-Strike 2	45−50 +50%	30−33 −50%
Dota 2	182 +51.7%	120−130 −51.7%
Grand Theft Auto V	182 +51.7%	120−130 −51.7%
Metro Exodus	76 +52%	50−55 −52%
PLAYERUNKNOWN'S BATTLEGROUNDS	200−210 +49.3%	140−150 −49.3%
Red Dead Redemption 2	63 +57.5%	40−45 −57.5%
The Witcher 3: Wild Hunt	182 +51.7%	120−130 −51.7%

4K
Ultra Preset

Battlefield 5	90−95 +51.7%	60−65 −51.7%
Counter-Strike 2	45−50 +50%	30−33 −50%
Cyberpunk 2077	46 +53.3%	30−33 −53.3%
Dota 2	211 +50.7%	140−150 −50.7%
Far Cry 5	100−110 +50%	70−75 −50%
Fortnite	95−100 +47.7%	65−70 −47.7%
Forza Horizon 4	161 +46.4%	110−120 −46.4%
Forza Horizon 5	80−85 +52.7%	55−60 −52.7%
Valorant	191 +46.9%	130−140 −46.9%

This is how RTX 3080 Ti and L40S compete in popular games:

RTX 3080 Ti is 53% faster in 1080p
RTX 3080 Ti is 46% faster in 1440p
RTX 3080 Ti is 51% faster in 4K

Pros & cons summary

Performance score	68.23	47.67
Recency	31 May 2021	13 October 2022
Maximum RAM amount	12 GB	48 GB
Chip lithography	8 nm	5 nm
Power consumption (TDP)	350 Watt	300 Watt

RTX 3080 Ti has a 43.1% higher aggregate performance score.

L40S, on the other hand, has an age advantage of 1 year, a 300% higher maximum VRAM amount, a 60% more advanced lithography process, and 16.7% lower power consumption.

The GeForce RTX 3080 Ti is our recommended choice as it beats the L40S in performance tests.

Be aware that GeForce RTX 3080 Ti is a desktop card while L40S is a workstation one.

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