GeForce RTX 5090 vs Radeon HD 6670

Place in the ranking	916	6
Place by popularity	not in top-100	58
Cost-effectiveness evaluation	0.08	8.97
Power efficiency	1.96	no data
Architecture	TeraScale 2 (2009−2015)	Blackwell 2.0 (2025)
GPU code name	Turks	GB202
Market segment	Desktop	Desktop
Design	reference	no data
Release date	19 April 2011 (13 years ago)	30 January 2025 (recently)
Launch price (MSRP)	$99	$1,999

Cost-effectiveness evaluation

Performance to price ratio. The higher, the better.

RTX 5090 has 11113% better value for money than HD 6670.

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	480	21760
Core clock speed	no data	2017 MHz
Boost clock speed	800 MHz	2407 MHz
Number of transistors	716 million	92,200 million
Manufacturing process technology	40 nm	5 nm
Power consumption (TDP)	66 Watt	575 Watt
Texture fill rate	19.20	1,637
Floating-point processing power	0.768 TFLOPS	104.8 TFLOPS
ROPs	8	176
TMUs	24	680
Tensor Cores	no data	680
Ray Tracing Cores	no data	170

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).

Bus support	PCIe 2.0 x16	no data
Interface	PCIe 2.0 x16	PCIe 5.0 x16
Length	168 mm	304 mm
Width	1-slot	2-slot
Supplementary power connectors	None	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	GDDR7
Maximum RAM amount	1 GB	32 GB
Memory bus width	128 Bit	512 Bit
Memory clock speed	1050 MHz	1750 MHz
Memory bandwidth	64 GB/s	1.79 TB/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	1x DVI, 1x HDMI, 1x VGA	1x HDMI 2.1b, 3x DisplayPort 2.1b
Eyefinity	+	-
HDMI	+	+

Supported technologies

Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.

CrossFire

API compatibility

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

DirectX	DirectX® 11	12 Ultimate (12_2)
Shader Model	5.0	6.8
OpenGL	4.4	4.6
OpenCL	1.2	3.0
Vulkan	-	1.4
CUDA	-	10.1

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.

HD 6670 1.86

RTX 5090 82.26
+4323%

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.

HD 6670 724

RTX 5090 32021
+4323%

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	4−5 −5075%	207 +5075%
1440p	4−5 −4500%	184 +4500%
4K	3−4 −4600%	141 +4600%

Cost per frame, $

1080p	24.75 −156%	9.66 +156%
1440p	24.75 −128%	10.86 +128%
4K	33.00 −133%	14.18 +133%

RTX 5090 has 156% lower cost per frame in 1080p
RTX 5090 has 128% lower cost per frame in 1440p
RTX 5090 has 133% lower cost per frame in 4K

FPS performance in popular games

Full HD
Low Preset

Counter-Strike 2

6−7

+0%

6−7

+0%

Full HD
Medium Preset

Counter-Strike 2	6−7 +0%	6−7 +0%
Red Dead Redemption 2	3−4 +0%	3−4 +0%

Full HD
High Preset

Counter-Strike 2	6−7 +0%	6−7 +0%
Far Cry 5	159 +0%	159 +0%
PLAYERUNKNOWN'S BATTLEGROUNDS	4−5 +0%	4−5 +0%
Red Dead Redemption 2	3−4 +0%	3−4 +0%
The Witcher 3: Wild Hunt	4−5 +0%	4−5 +0%
World of Tanks	8−9 +0%	8−9 +0%

Full HD
Ultra Preset

Counter-Strike 2	202 +0%	202 +0%
Far Cry 5	6−7 +0%	6−7 +0%
PLAYERUNKNOWN'S BATTLEGROUNDS	4−5 +0%	4−5 +0%

1440p
High Preset

Counter-Strike 2

183

+0%

183

+0%

1440p
Ultra Preset

Far Cry 5	4−5 +0%	4−5 +0%
Valorant	4−5 +0%	4−5 +0%

4K
High Preset

Counter-Strike 2	174 +0%	174 +0%
Dota 2	14−16 +0%	14−16 +0%
Metro Exodus	167 +0%	167 +0%

4K
Ultra Preset

Counter-Strike 2	55 +0%	55 +0%
Valorant	0−1	0−1

This is how HD 6670 and RTX 5090 compete in popular games:

RTX 5090 is 5075% faster in 1080p
RTX 5090 is 4500% faster in 1440p
RTX 5090 is 4600% faster in 4K

All in all, in popular games:

there's a draw in 19 tests (100%)

Pros & cons summary

Performance score	1.86	82.26
Recency	19 April 2011	30 January 2025
Maximum RAM amount	1 GB	32 GB
Chip lithography	40 nm	5 nm
Power consumption (TDP)	66 Watt	575 Watt

HD 6670 has 771.2% lower power consumption.

RTX 5090, on the other hand, has a 4322.6% higher aggregate performance score, an age advantage of 13 years, a 3100% higher maximum VRAM amount, and a 700% more advanced lithography process.

The GeForce RTX 5090 is our recommended choice as it beats the Radeon HD 6670 in performance tests.

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