GeForce RTX 4090 vs Radeon HD 7640G
Aggregate performance score
We've compared Radeon HD 7640G with GeForce RTX 4090, including specs and performance data.
RTX 4090 outperforms HD 7640G by a whopping 8303% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 1062 | 1 |
| Place by popularity | not in top-100 | 6 |
| Cost-effectiveness evaluation | no data | 18.83 |
| Power efficiency | 2.34 | 15.30 |
| Architecture | TeraScale 3 (2010−2013) | Ada Lovelace (2022−2024) |
| GPU code name | Devastator Lite | AD102 |
| Market segment | Laptop | Desktop |
| Release date | 15 May 2012 (12 years ago) | 20 September 2022 (2 years ago) |
| Launch price (MSRP) | no data | $1,599 |
Cost-effectiveness evaluation
Performance to price ratio. The higher, the better.
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 | 256 | 16384 |
| Core clock speed | 496 MHz | 2235 MHz |
| Boost clock speed | 685 MHz | 2520 MHz |
| Number of transistors | 1,303 million | 76,300 million |
| Manufacturing process technology | 32 nm | 5 nm |
| Power consumption (TDP) | 35 Watt | 450 Watt |
| Texture fill rate | 10.96 | 1,290 |
| Floating-point processing power | 0.3507 TFLOPS | 82.58 TFLOPS |
| ROPs | 8 | 176 |
| TMUs | 16 | 512 |
| Tensor Cores | no data | 512 |
| Ray Tracing Cores | no data | 128 |
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).
| Laptop size | medium sized | no data |
| Interface | IGP | PCIe 4.0 x16 |
| Length | no data | 304 mm |
| Width | no data | 3-slot |
| Supplementary power connectors | no data | 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 | System Shared | GDDR6X |
| Maximum RAM amount | System Shared | 24 GB |
| Memory bus width | System Shared | 384 Bit |
| Memory clock speed | System Shared | 1313 MHz |
| Memory bandwidth | no data | 1.01 TB/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 | No outputs | 1x HDMI 2.1, 3x DisplayPort 1.4a |
| HDMI | - | + |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 11.2 (11_0) | 12 Ultimate (12_2) |
| Shader Model | 5.0 | 6.8 |
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | N/A | 1.3 |
| 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.
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.
3DMark 11 Performance GPU
3DMark 11 is an obsolete DirectX 11 benchmark by Futuremark. It used four tests based on two scenes, one being few submarines exploring the submerged wreck of a sunken ship, the other is an abandoned temple deep in the jungle. All the tests are heavy with volumetric lighting and tessellation, and despite being done in 1280x720 resolution, are relatively taxing. Discontinued in January 2020, 3DMark 11 is now superseded by Time Spy.
3DMark Vantage Performance
3DMark Vantage is an outdated DirectX 10 benchmark using 1280x1024 screen resolution. It taxes the graphics card with two scenes, one depicting a girl escaping some militarized base located within a sea cave, the other displaying a space fleet attack on a defenseless planet. It was discontinued in April 2017, and Time Spy benchmark is now recommended to be used instead.
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 | 3−4
−8500%
| 258
+8500%
|
| 1440p | 2−3
−9800%
| 198
+9800%
|
| 4K | 1−2
−14100%
| 142
+14100%
|
Cost per frame, $
| 1080p | no data | 6.20 |
| 1440p | no data | 8.08 |
| 4K | no data | 11.26 |
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 10−11
−2020%
|
212
+2020%
|
| Cyberpunk 2077 | 4−5
−5525%
|
225
+5525%
|
Full HD
Medium Preset
| Battlefield 5 | 1−2
−11600%
|
110−120
+11600%
|
| Counter-Strike 2 | 10−11
−2050%
|
215
+2050%
|
| Cyberpunk 2077 | 4−5
−2675%
|
111
+2675%
|
| Forza Horizon 4 | 8−9
−6838%
|
555
+6838%
|
| Red Dead Redemption 2 | 6−7
−2500%
|
150−160
+2500%
|
Full HD
High Preset
| Battlefield 5 | 1−2
−11600%
|
110−120
+11600%
|
| Counter-Strike 2 | 10−11
−1890%
|
199
+1890%
|
| Cyberpunk 2077 | 4−5
−2575%
|
107
+2575%
|
| Dota 2 | 1−2
−19900%
|
200
+19900%
|
| Far Cry 5 | 10−11
−1390%
|
149
+1390%
|
| Fortnite | 5−6
−6060%
|
300−350
+6060%
|
| Forza Horizon 4 | 8−9
−6750%
|
548
+6750%
|
| Grand Theft Auto V | 1−2
−17300%
|
174
+17300%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−1554%
|
210−220
+1554%
|
| Red Dead Redemption 2 | 6−7
−2500%
|
150−160
+2500%
|
| The Witcher 3: Wild Hunt | 7−8
−2386%
|
170−180
+2386%
|
| World of Tanks | 24−27
−973%
|
270−280
+973%
|
Full HD
Ultra Preset
| Battlefield 5 | 1−2
−11600%
|
110−120
+11600%
|
| Counter-Strike 2 | 10−11
−1790%
|
189
+1790%
|
| Cyberpunk 2077 | 4−5
−2525%
|
105
+2525%
|
| Dota 2 | 1−2
−22300%
|
224
+22300%
|
| Far Cry 5 | 10−11
−2040%
|
210−220
+2040%
|
| Forza Horizon 4 | 8−9
−6700%
|
544
+6700%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−1554%
|
210−220
+1554%
|
1440p
High Preset
| PLAYERUNKNOWN'S BATTLEGROUNDS | 7−8
−2400%
|
170−180
+2400%
|
| Red Dead Redemption 2 | 0−1 | 90−95 |
| World of Tanks | 6−7
−8500%
|
500−550
+8500%
|
1440p
Ultra Preset
| Counter-Strike 2 | 1−2
−7900%
|
80−85
+7900%
|
| Cyberpunk 2077 | 3−4
−2467%
|
77
+2467%
|
| Far Cry 5 | 5−6
−3100%
|
160−170
+3100%
|
| Forza Horizon 5 | 0−1 | 239 |
| The Witcher 3: Wild Hunt | 4−5
−6450%
|
262
+6450%
|
| Valorant | 6−7
−9433%
|
572
+9433%
|
4K
High Preset
| Counter-Strike 2 | 8−9
−1525%
|
130
+1525%
|
| Dota 2 | 14−16
−1147%
|
187
+1147%
|
| Grand Theft Auto V | 14−16
−1147%
|
187
+1147%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 3−4
−6867%
|
200−210
+6867%
|
| Red Dead Redemption 2 | 0−1 | 60−65 |
| The Witcher 3: Wild Hunt | 14−16
−1147%
|
187
+1147%
|
4K
Ultra Preset
| Battlefield 5 | 1−2
−9000%
|
90−95
+9000%
|
| Counter-Strike 2 | 8−9
−375%
|
38
+375%
|
| Cyberpunk 2077 | 2−3
−1900%
|
40
+1900%
|
| Dota 2 | 14−16
−1413%
|
227
+1413%
|
| Far Cry 5 | 0−1 | 100−110 |
| Valorant | 1−2
−36300%
|
364
+36300%
|
Full HD
Medium Preset
| Forza Horizon 5 | 309
+0%
|
309
+0%
|
| Metro Exodus | 178
+0%
|
178
+0%
|
| Valorant | 826
+0%
|
826
+0%
|
Full HD
High Preset
| Forza Horizon 5 | 329
+0%
|
329
+0%
|
| Metro Exodus | 183
+0%
|
183
+0%
|
| Valorant | 750−800
+0%
|
750−800
+0%
|
Full HD
Ultra Preset
| Forza Horizon 5 | 279
+0%
|
279
+0%
|
| Valorant | 680
+0%
|
680
+0%
|
1440p
High Preset
| Counter-Strike 2 | 30−35
+0%
|
30−35
+0%
|
| Dota 2 | 162
+0%
|
162
+0%
|
| Grand Theft Auto V | 161
+0%
|
161
+0%
|
1440p
Ultra Preset
| Battlefield 5 | 85−90
+0%
|
85−90
+0%
|
| Forza Horizon 4 | 507
+0%
|
507
+0%
|
| Metro Exodus | 152
+0%
|
152
+0%
|
4K
High Preset
| Metro Exodus | 137
+0%
|
137
+0%
|
4K
Ultra Preset
| Fortnite | 95−100
+0%
|
95−100
+0%
|
| Forza Horizon 4 | 284
+0%
|
284
+0%
|
| Forza Horizon 5 | 161
+0%
|
161
+0%
|
This is how HD 7640G and RTX 4090 compete in popular games:
- RTX 4090 is 8500% faster in 1080p
- RTX 4090 is 9800% faster in 1440p
- RTX 4090 is 14100% faster in 4K
Here's the range of performance differences observed across popular games:
- in Valorant, with 4K resolution and the Ultra Preset, the RTX 4090 is 36300% faster.
All in all, in popular games:
- RTX 4090 is ahead in 42 tests (70%)
- there's a draw in 18 tests (30%)
Pros & cons summary
| Performance score | 1.19 | 100.00 |
| Recency | 15 May 2012 | 20 September 2022 |
| Chip lithography | 32 nm | 5 nm |
| Power consumption (TDP) | 35 Watt | 450 Watt |
HD 7640G has 1185.7% lower power consumption.
RTX 4090, on the other hand, has a 8303.4% higher aggregate performance score, an age advantage of 10 years, and a 540% more advanced lithography process.
The GeForce RTX 4090 is our recommended choice as it beats the Radeon HD 7640G in performance tests.
Be aware that Radeon HD 7640G is a notebook card while GeForce RTX 4090 is a desktop one.
Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
