Radeon RX 9070 XT vs HD 6650M
Aggregate performance score
We've compared Radeon HD 6650M with Radeon RX 9070 XT, including specs and performance data.
9070 XT outperforms HD 6650M by a whopping 3417% 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 | 957 | 32 |
| Place by popularity | not in top-100 | 80 |
| Cost-effectiveness evaluation | no data | 63.05 |
| Power efficiency | no data | 16.26 |
| Architecture | TeraScale 2 (2009−2015) | RDNA 4.0 (2025) |
| GPU code name | Whistler | Navi 48 |
| Market segment | Laptop | Desktop |
| Release date | 4 January 2011 (14 years ago) | 6 March 2025 (less than a year ago) |
| Launch price (MSRP) | no data | $599 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
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 | 4096 |
| Core clock speed | 600 MHz | 1660 MHz |
| Boost clock speed | no data | 2970 MHz |
| Number of transistors | 716 million | 53,900 million |
| Manufacturing process technology | 40 nm | 4 nm |
| Power consumption (TDP) | no data | 304 Watt |
| Texture fill rate | 14.40 | 760.3 |
| Floating-point processing power | 0.576 TFLOPS | 48.66 TFLOPS |
| ROPs | 8 | 128 |
| TMUs | 24 | 256 |
| Tensor Cores | no data | 128 |
| Ray Tracing Cores | no data | 64 |
| L0 Cache | no data | 1 MB |
| L1 Cache | 48 KB | no data |
| L2 Cache | 256 KB | 8 MB |
| L3 Cache | no data | 64 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 | medium sized | no data |
| Interface | PCIe 2.0 x16 | PCIe 5.0 x16 |
| Length | no data | 267 mm |
| Width | no data | 2-slot |
| Supplementary power connectors | no data | 2x 8-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 | DDR3 | GDDR6 |
| Maximum RAM amount | 1 GB | 16 GB |
| Memory bus width | 128 Bit | 256 Bit |
| Memory clock speed | 800 MHz | 2518 MHz |
| Memory bandwidth | 25.6 GB/s | 644.6 GB/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 2.1b, 3x DisplayPort 2.1a |
| HDMI | - | + |
API and SDK support
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 | 2.2 |
| Vulkan | N/A | 1.4 |
| 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 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:
| 900p | 19
−3321%
| 650−700
+3321%
|
| Full HD | 18
−1089%
| 214
+1089%
|
| 1440p | 3−4
−4100%
| 126
+4100%
|
| 4K | 2−3
−3900%
| 80
+3900%
|
Cost per frame, $
| 1080p | no data | 2.80 |
| 1440p | no data | 4.75 |
| 4K | no data | 7.49 |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 3−4
−10200%
|
300−350
+10200%
|
| Cyberpunk 2077 | 4−5
−3975%
|
160−170
+3975%
|
Full HD
Medium
| Battlefield 5 | 4−5
−4275%
|
170−180
+4275%
|
| Counter-Strike 2 | 3−4
−10200%
|
300−350
+10200%
|
| Cyberpunk 2077 | 4−5
−3975%
|
160−170
+3975%
|
| Escape from Tarkov | 6−7
−1917%
|
120−130
+1917%
|
| Far Cry 5 | 5−6
−5820%
|
296
+5820%
|
| Fortnite | 8−9
−3675%
|
300−350
+3675%
|
| Forza Horizon 4 | 10−11
−2470%
|
250−260
+2470%
|
| Forza Horizon 5 | 3−4
−6400%
|
190−200
+6400%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 10−12
−1482%
|
170−180
+1482%
|
| Valorant | 35−40
−866%
|
350−400
+866%
|
Full HD
High
| Battlefield 5 | 4−5
−4275%
|
170−180
+4275%
|
| Counter-Strike 2 | 3−4
−10200%
|
300−350
+10200%
|
| Counter-Strike: Global Offensive | 35−40
−632%
|
270−280
+632%
|
| Cyberpunk 2077 | 4−5
−3975%
|
160−170
+3975%
|
| Dota 2 | 21−24
−3233%
|
700−750
+3233%
|
| Escape from Tarkov | 6−7
−1917%
|
120−130
+1917%
|
| Far Cry 5 | 5−6
−5600%
|
285
+5600%
|
| Fortnite | 8−9
−3675%
|
300−350
+3675%
|
| Forza Horizon 4 | 10−11
−2470%
|
250−260
+2470%
|
| Forza Horizon 5 | 3−4
−6400%
|
190−200
+6400%
|
| Grand Theft Auto V | 3−4
−5533%
|
160−170
+5533%
|
| Metro Exodus | 3−4
−5433%
|
160−170
+5433%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 10−12
−1482%
|
170−180
+1482%
|
| The Witcher 3: Wild Hunt | 8−9
−6113%
|
497
+6113%
|
| Valorant | 35−40
−866%
|
350−400
+866%
|
Full HD
Ultra
| Battlefield 5 | 4−5
−4275%
|
170−180
+4275%
|
| Cyberpunk 2077 | 4−5
−3975%
|
160−170
+3975%
|
| Dota 2 | 21−24
−3233%
|
700−750
+3233%
|
| Escape from Tarkov | 6−7
−1917%
|
120−130
+1917%
|
| Far Cry 5 | 5−6
−5300%
|
270
+5300%
|
| Forza Horizon 4 | 10−11
−2470%
|
250−260
+2470%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 10−12
−1482%
|
170−180
+1482%
|
| The Witcher 3: Wild Hunt | 8−9
−3350%
|
276
+3350%
|
| Valorant | 35−40
−866%
|
350−400
+866%
|
Full HD
Epic
| Fortnite | 8−9
−3675%
|
300−350
+3675%
|
1440p
High
| Counter-Strike 2 | 5−6
−3860%
|
190−200
+3860%
|
| Counter-Strike: Global Offensive | 12−14
−3823%
|
500−550
+3823%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
−872%
|
170−180
+872%
|
| Valorant | 12−14
−3408%
|
450−500
+3408%
|
1440p
Ultra
| Cyberpunk 2077 | 1−2
−9200%
|
90−95
+9200%
|
| Escape from Tarkov | 4−5
−2900%
|
120−130
+2900%
|
| Far Cry 5 | 3−4
−8567%
|
260
+8567%
|
| Forza Horizon 4 | 5−6
−4320%
|
220−230
+4320%
|
| The Witcher 3: Wild Hunt | 3−4
−6967%
|
212
+6967%
|
1440p
Epic
| Fortnite | 3−4
−4933%
|
150−160
+4933%
|
4K
High
| Grand Theft Auto V | 14−16
−1029%
|
150−160
+1029%
|
| Valorant | 9−10
−3556%
|
300−350
+3556%
|
4K
Ultra
| Dota 2 | 4−5
−3400%
|
140−150
+3400%
|
| Escape from Tarkov | 0−1 | 80−85 |
| Far Cry 5 | 0−1 | 152 |
| Forza Horizon 4 | 0−1 | 170−180 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 3−4
−3100%
|
95−100
+3100%
|
4K
Epic
| Fortnite | 3−4
−2533%
|
75−80
+2533%
|
1440p
High
| Grand Theft Auto V | 130−140
+0%
|
130−140
+0%
|
| Metro Exodus | 110−120
+0%
|
110−120
+0%
|
1440p
Ultra
| Battlefield 5 | 160−170
+0%
|
160−170
+0%
|
4K
High
| Counter-Strike 2 | 85−90
+0%
|
85−90
+0%
|
| Metro Exodus | 70−75
+0%
|
70−75
+0%
|
| The Witcher 3: Wild Hunt | 174
+0%
|
174
+0%
|
4K
Ultra
| Battlefield 5 | 120−130
+0%
|
120−130
+0%
|
| Counter-Strike 2 | 85−90
+0%
|
85−90
+0%
|
| Cyberpunk 2077 | 45−50
+0%
|
45−50
+0%
|
This is how HD 6650M and RX 9070 XT compete in popular games:
- RX 9070 XT is 3321% faster in 900p
- RX 9070 XT is 1089% faster in 1080p
- RX 9070 XT is 4100% faster in 1440p
- RX 9070 XT is 3900% faster in 4K
Here's the range of performance differences observed across popular games:
- in Counter-Strike 2, with 1080p resolution and the Low Preset, the RX 9070 XT is 10200% faster.
All in all, in popular games:
- RX 9070 XT performs better in 49 tests (84%)
- there's a draw in 9 tests (16%)
Pros & cons summary
| Performance score | 1.83 | 64.37 |
| Recency | 4 January 2011 | 6 March 2025 |
| Maximum RAM amount | 1 GB | 16 GB |
| Chip lithography | 40 nm | 4 nm |
RX 9070 XT has a 3417.5% higher aggregate performance score, an age advantage of 14 years, a 1500% higher maximum VRAM amount, and a 900% more advanced lithography process.
The Radeon RX 9070 XT is our recommended choice as it beats the Radeon HD 6650M in performance tests.
Be aware that Radeon HD 6650M is a notebook graphics card while Radeon RX 9070 XT 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.
