GeForce RTX 4090 vs 9650M GS
Aggregate performance score
We've compared GeForce 9650M GS with GeForce RTX 4090, including specs and performance data.
RTX 4090 outperforms 9650M GS by a whopping 13948% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 1261 | 3 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 31.29 |
| Power efficiency | 1.73 | 15.70 |
| Architecture | Tesla (2006−2010) | Ada Lovelace (2022−2024) |
| GPU code name | G84 | AD102 |
| Market segment | Laptop | Desktop |
| Release date | 13 March 2008 (18 years ago) | 20 September 2022 (3 years ago) |
| Launch price (MSRP) | no data | $1,599 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
Currently popular graphics cards are shown for comparison.
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.
| Pipelines / CUDA cores | 32 | 16384 |
| Core clock speed | 625 MHz | 2235 MHz |
| Boost clock speed | no data | 2520 MHz |
| Number of transistors | 289 million | 76,300 million |
| Manufacturing process technology | 80 nm | 5 nm |
| Power consumption (TDP) | 29 Watt | 450 Watt |
| Texture fill rate | 10.00 | 1,290.2 |
| Floating-point processing power | 0.08 TFLOPS | 82.58 TFLOPS |
| ROPs | 8 | 176 |
| TMUs | 16 | 512 |
| Tensor Cores | no data | 512 |
| Ray Tracing Cores | no data | 128 |
| L1 Cache | no data | 16 MB |
| L2 Cache | 32 KB | 72 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).
| Laptop size | large | no data |
| Interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
| Length | no data | 304 mm |
| Width | no data | 3-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 | GDDR3 | GDDR6X |
| Maximum RAM amount | 512 MB | 24 GB |
| Memory bus width | 128 Bit | 384 Bit |
| Memory clock speed | 800 MHz | 1313 MHz |
| Memory bandwidth | 25.6 GB/s | 1.01 TB/s |
| Shared memory | - | - |
| 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 | 1x HDMI 2.1, 3x DisplayPort 1.4a |
| HDMI | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 11.1 (10_0) | 12 Ultimate (12_2) |
| Shader Model | 4.0 | 6.8 |
| OpenGL | 3.3 | 4.6 |
| OpenCL | 1.1 | 3.0 |
| Vulkan | N/A | 1.4 |
| CUDA | 1.1 | 8.9 |
| DLSS | - | + |
Synthetic benchmarks
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.
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 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 | 1−2
−24500%
| 246
+24500%
|
| 1440p | 1−2
−18300%
| 184
+18300%
|
| 4K | 0−1 | 134 |
Cost per frame, $
| 1080p | no data | 6.50 |
| 1440p | no data | 8.69 |
| 4K | no data | 11.93 |
FPS performance in popular games
Full HD
Low
| Cyberpunk 2077 | 1−2
−22600%
|
227
+22600%
|
| Palworld | 3−4
−7900%
|
240
+7900%
|
Full HD
Medium
| Cyberpunk 2077 | 1−2
−22300%
|
224
+22300%
|
| Forza Horizon 4 | 5−6
−6780%
|
300−350
+6780%
|
| Palworld | 3−4
−7867%
|
239
+7867%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 8−9
−2063%
|
170−180
+2063%
|
| Valorant | 27−30
−2329%
|
650−700
+2329%
|
Full HD
High
| Counter-Strike: Global Offensive | 18−20
−1363%
|
270−280
+1363%
|
| Cyberpunk 2077 | 1−2
−21400%
|
215
+21400%
|
| Dota 2 | 12−14
−2008%
|
253
+2008%
|
| Forza Horizon 4 | 5−6
−6780%
|
300−350
+6780%
|
| Metro Exodus | 0−1 | 230 |
| Palworld | 3−4
−7700%
|
234
+7700%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 8−9
−2063%
|
170−180
+2063%
|
| The Witcher 3: Wild Hunt | 6−7
−9533%
|
578
+9533%
|
| Valorant | 27−30
−2329%
|
650−700
+2329%
|
Full HD
Ultra
| Cyberpunk 2077 | 1−2
−21000%
|
211
+21000%
|
| Dota 2 | 12−14
−1767%
|
224
+1767%
|
| Forza Horizon 4 | 5−6
−6780%
|
300−350
+6780%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 8−9
−2063%
|
170−180
+2063%
|
| The Witcher 3: Wild Hunt | 6−7
−4983%
|
305
+4983%
|
| Valorant | 27−30
−2329%
|
680
+2329%
|
Full HD
Epic
| Palworld | 3−4
−7633%
|
232
+7633%
|
1440p
High
| Counter-Strike 2 | 2−3
−15500%
|
312
+15500%
|
| Counter-Strike: Global Offensive | 3−4
−17100%
|
500−550
+17100%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 7−8
−2400%
|
170−180
+2400%
|
1440p
Ultra
| Forza Horizon 4 | 1−2
−30500%
|
300−350
+30500%
|
| The Witcher 3: Wild Hunt | 1−2
−26100%
|
262
+26100%
|
1440p
Epic
| Fortnite | 1−2
−15000%
|
150−160
+15000%
|
| Palworld | 1−2
−21000%
|
211
+21000%
|
4K
High
| Grand Theft Auto V | 14−16
−1147%
|
187
+1147%
|
| Valorant | 6−7
−5217%
|
300−350
+5217%
|
4K
Ultra
| PLAYERUNKNOWN'S BATTLEGROUNDS | 2−3
−4700%
|
95−100
+4700%
|
4K
Epic
| Fortnite | 2−3
−3850%
|
75−80
+3850%
|
Full HD
Low
| Counter-Strike 2 | 351
+0%
|
351
+0%
|
| Resident Evil 4 Remake | 351
+0%
|
351
+0%
|
Full HD
Medium
| Battlefield 5 | 190−200
+0%
|
190−200
+0%
|
| Counter-Strike 2 | 340
+0%
|
340
+0%
|
| Far Cry 5 | 209
+0%
|
209
+0%
|
| Fortnite | 300−350
+0%
|
300−350
+0%
|
Full HD
High
| Battlefield 5 | 190−200
+0%
|
190−200
+0%
|
| Counter-Strike 2 | 340
+0%
|
340
+0%
|
| Far Cry 5 | 201
+0%
|
201
+0%
|
| Fortnite | 300−350
+0%
|
300−350
+0%
|
| Grand Theft Auto V | 174
+0%
|
174
+0%
|
Full HD
Ultra
| Battlefield 5 | 190−200
+0%
|
190−200
+0%
|
| Far Cry 5 | 187
+0%
|
187
+0%
|
Full HD
Epic
| Fortnite | 300−350
+0%
|
300−350
+0%
|
1440p
High
| Grand Theft Auto V | 162
+0%
|
162
+0%
|
| Metro Exodus | 180
+0%
|
180
+0%
|
| Valorant | 450−500
+0%
|
450−500
+0%
|
1440p
Ultra
| Battlefield 5 | 190−200
+0%
|
190−200
+0%
|
| Cyberpunk 2077 | 159
+0%
|
159
+0%
|
| Far Cry 5 | 187
+0%
|
187
+0%
|
4K
High
| Counter-Strike 2 | 166
+0%
|
166
+0%
|
| Metro Exodus | 137
+0%
|
137
+0%
|
| Palworld | 198
+0%
|
198
+0%
|
| The Witcher 3: Wild Hunt | 281
+0%
|
281
+0%
|
4K
Ultra
| Battlefield 5 | 130−140
+0%
|
130−140
+0%
|
| Counter-Strike 2 | 140−150
+0%
|
140−150
+0%
|
| Cyberpunk 2077 | 81
+0%
|
81
+0%
|
| Dota 2 | 227
+0%
|
227
+0%
|
| Far Cry 5 | 170
+0%
|
170
+0%
|
| Forza Horizon 4 | 300−350
+0%
|
300−350
+0%
|
4K
Epic
| Palworld | 139
+0%
|
139
+0%
|
This is how 9650M GS and RTX 4090 compete in popular games:
- RTX 4090 is 24500% faster in 1080p
- RTX 4090 is 18300% faster in 1440p
Here's the range of performance differences observed across popular games:
- in Forza Horizon 4, with 1440p resolution and the Ultra Preset, the RTX 4090 is 30500% faster.
All in all, in popular games:
- RTX 4090 performs better in 33 tests (52%)
- there's a draw in 31 tests (48%)
Pros & cons summary
| Performance score | 0.65 | 91.31 |
| Recency | 13 March 2008 | 20 September 2022 |
| Maximum RAM amount | 512 MB | 24 GB |
| Chip lithography | 80 nm | 5 nm |
| Power consumption (TDP) | 29 Watt | 450 Watt |
9650M GS has 1452% lower power consumption.
RTX 4090, on the other hand, has a 13948% higher aggregate performance score, an age advantage of 14 years, a 4700% higher maximum VRAM amount, and a 1500% more advanced lithography process.
The GeForce RTX 4090 is our recommended choice as it beats the GeForce 9650M GS in performance tests.
Be aware that GeForce 9650M GS is a notebook graphics card while GeForce RTX 4090 is a desktop one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
