Riva TNT2 vs GeForce RTX 4090

Place in the ranking	1	1522
Place by popularity	6	not in top-100
Cost-effectiveness evaluation	18.56	no data
Power efficiency	15.30	no data
Architecture	Ada Lovelace (2022−2024)	Fahrenheit (1998−2000)
GPU code name	AD102	NV5
Market segment	Desktop	Desktop
Release date	20 September 2022 (2 years ago)	12 October 1999 (25 years ago)
Launch price (MSRP)	$1,599	no data

Cost-effectiveness evaluation

Performance to price ratio. The higher, the better.

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	16384	no data
Core clock speed	2235 MHz	125 MHz
Boost clock speed	2520 MHz	no data
Number of transistors	76,300 million	15 million
Manufacturing process technology	5 nm	250 nm
Power consumption (TDP)	450 Watt	no data
Texture fill rate	1,290	0.25
Floating-point processing power	82.58 TFLOPS	no data
ROPs	176	2
TMUs	512	2
Tensor Cores	512	no data
Ray Tracing Cores	128	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 4.0 x16	AGP 4x
Length	304 mm	no data
Width	3-slot	1-slot
Supplementary power connectors	1x 16-pin	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	GDDR6X	SDR
Maximum RAM amount	24 GB	16 MB
Memory bus width	384 Bit	128 Bit
Memory clock speed	1313 MHz	150 MHz
Memory bandwidth	1.01 TB/s	2.4 GB/s
Shared memory	-	no data

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

API compatibility

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

DirectX	12 Ultimate (12_2)	6.0
Shader Model	6.8	no data
OpenGL	4.6	1.2
OpenCL	3.0	N/A
Vulkan	1.3	N/A
CUDA	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 4090 100.00
+999900%

Riva TNT2 0.01

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 4090 38443
+1281333%

Riva TNT2 3

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	258	-0−1
1440p	197	-0−1
4K	143	-0−1

Cost per frame, $

1080p	6.20	no data
1440p	8.12	no data
4K	11.18	no data

FPS performance in popular games

Full HD
Low Preset

Counter-Strike 2	212	0−1
Cyberpunk 2077	225	0−1
Elden Ring	249	0−1

Full HD
Medium Preset

Battlefield 5	110−120	0−1
Counter-Strike 2	215	0−1
Cyberpunk 2077	111	0−1
Forza Horizon 4	555	0−1
Metro Exodus	178	0−1
Red Dead Redemption 2	150−160	0−1
Valorant	826	0−1

Full HD
High Preset

Battlefield 5	110−120	0−1
Counter-Strike 2	199	0−1
Cyberpunk 2077	107	0−1
Dota 2	200	0−1
Elden Ring	468	0−1
Far Cry 5	149	0−1
Fortnite	300−350	0−1
Forza Horizon 4	548	0−1
Grand Theft Auto V	174	0−1
Metro Exodus	183	0−1
PLAYERUNKNOWN'S BATTLEGROUNDS	210−220	0−1
Red Dead Redemption 2	150−160	0−1
The Witcher 3: Wild Hunt	170−180	0−1
Valorant	750−800	0−1
World of Tanks	270−280	0−1

Full HD
Ultra Preset

Battlefield 5	110−120	0−1
Counter-Strike 2	185	0−1
Cyberpunk 2077	105	0−1
Dota 2	224	0−1
Far Cry 5	210−220	0−1
Forza Horizon 4	544	0−1
PLAYERUNKNOWN'S BATTLEGROUNDS	210−220	0−1
Valorant	680	0−1

1440p
High Preset

Dota 2	162	0−1
Elden Ring	343	0−1
Grand Theft Auto V	161	0−1
PLAYERUNKNOWN'S BATTLEGROUNDS	170−180	0−1
Red Dead Redemption 2	90−95	0−1
World of Tanks	500−550	0−1

1440p
Ultra Preset

Battlefield 5	85−90	0−1
Counter-Strike 2	152	0−1
Cyberpunk 2077	77	0−1
Far Cry 5	160−170	0−1
Forza Horizon 4	507	0−1
Metro Exodus	152	0−1
The Witcher 3: Wild Hunt	262	0−1
Valorant	572	0−1

4K
High Preset

Counter-Strike 2	166	0−1
Dota 2	187	0−1
Elden Ring	198	0−1
Grand Theft Auto V	187	0−1
Metro Exodus	137	0−1
PLAYERUNKNOWN'S BATTLEGROUNDS	200−210	0−1
Red Dead Redemption 2	60−65	0−1
The Witcher 3: Wild Hunt	187	0−1

4K
Ultra Preset

Battlefield 5	90−95	0−1
Counter-Strike 2	150−160	0−1
Cyberpunk 2077	40	0−1
Dota 2	227	0−1
Far Cry 5	100−110	0−1
Fortnite	95−100	0−1
Forza Horizon 4	284	0−1
Valorant	364	0−1

Pros & cons summary

Performance score	100.00	0.01
Recency	20 September 2022	12 October 1999
Maximum RAM amount	24 GB	16 MB
Chip lithography	5 nm	250 nm

RTX 4090 has a 999900% higher aggregate performance score, an age advantage of 22 years, a 153500% higher maximum VRAM amount, and a 4900% more advanced lithography process.

The GeForce RTX 4090 is our recommended choice as it beats the Riva TNT2 in performance tests.

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