Radeon RX 7900 XTX vs HD 7970M Crossfire
Aggregate performance score
We've compared Radeon HD 7970M Crossfire with Radeon RX 7900 XTX, including specs and performance data.
RX 7900 XTX outperforms HD 7970M Crossfire by a whopping 404% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 347 | 8 |
| Place by popularity | not in top-100 | 53 |
| Cost-effectiveness evaluation | no data | 34.86 |
| Power efficiency | 5.49 | 15.60 |
| Architecture | GCN (2012−2015) | RDNA 3.0 (2022−2025) |
| GPU code name | Wimbledon XT | Navi 31 |
| Market segment | Laptop | Desktop |
| Release date | 1 May 2012 (12 years ago) | 3 November 2022 (2 years ago) |
| Launch price (MSRP) | no data | $999 |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices 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. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 2560 | 6144 |
| Core clock speed | 850 MHz | 1929 MHz |
| Boost clock speed | no data | 2498 MHz |
| Number of transistors | no data | 57,700 million |
| Manufacturing process technology | 28 nm | 5 nm |
| Power consumption (TDP) | 200 Watt | 355 Watt |
| Texture fill rate | no data | 959.2 |
| Floating-point processing power | no data | 61.39 TFLOPS |
| ROPs | no data | 192 |
| TMUs | no data | 384 |
| Ray Tracing Cores | no data | 96 |
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 | no data | PCIe 4.0 x16 |
| Length | no data | 287 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 | GDDR5 | GDDR6 |
| Maximum RAM amount | no data | 24 GB |
| Memory bus width | 2x 256 Bit | 384 Bit |
| Memory clock speed | 4800 MHz | 2500 MHz |
| Memory bandwidth | no data | 960.0 GB/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 data | 1x HDMI 2.1a, 2x DisplayPort 2.1, 1x USB Type-C |
| HDMI | - | + |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 11.1 | 12 Ultimate (12_2) |
| Shader Model | no data | 6.7 |
| OpenGL | no data | 4.6 |
| OpenCL | no data | 2.2 |
| Vulkan | - | 1.3 |
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.
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 | 132
−392%
| 650−700
+392%
|
| Full HD | 102
−138%
| 243
+138%
|
| 1440p | 30−35
−447%
| 164
+447%
|
| 4K | 18−21
−461%
| 101
+461%
|
Cost per frame, $
| 1080p | no data | 4.11 |
| 1440p | no data | 6.09 |
| 4K | no data | 9.89 |
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 35−40
−845%
|
359
+845%
|
| Counter-Strike 2 | 27−30
−693%
|
214
+693%
|
| Cyberpunk 2077 | 30−35
−706%
|
250
+706%
|
Full HD
Medium Preset
| Atomic Heart | 35−40
−663%
|
290
+663%
|
| Battlefield 5 | 65−70
−192%
|
190−200
+192%
|
| Counter-Strike 2 | 27−30
−793%
|
241
+793%
|
| Cyberpunk 2077 | 30−35
−674%
|
240
+674%
|
| Far Cry 5 | 50−55
−316%
|
212
+316%
|
| Fortnite | 80−85
−260%
|
300−350
+260%
|
| Forza Horizon 4 | 60−65
−437%
|
338
+437%
|
| Forza Horizon 5 | 40−45
−556%
|
269
+556%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 55−60
−222%
|
170−180
+222%
|
| Valorant | 120−130
−270%
|
450−500
+270%
|
Full HD
High Preset
| Atomic Heart | 35−40
−424%
|
199
+424%
|
| Battlefield 5 | 65−70
−192%
|
190−200
+192%
|
| Counter-Strike 2 | 27−30
−715%
|
220
+715%
|
| Counter-Strike: Global Offensive | 200−210
−39%
|
270−280
+39%
|
| Cyberpunk 2077 | 30−35
−600%
|
217
+600%
|
| Dota 2 | 90−95
−110%
|
197
+110%
|
| Far Cry 5 | 50−55
−302%
|
205
+302%
|
| Fortnite | 80−85
−260%
|
300−350
+260%
|
| Forza Horizon 4 | 60−65
−424%
|
330
+424%
|
| Forza Horizon 5 | 40−45
−520%
|
254
+520%
|
| Grand Theft Auto V | 55−60
−207%
|
175
+207%
|
| Metro Exodus | 30−35
−671%
|
239
+671%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 55−60
−222%
|
170−180
+222%
|
| The Witcher 3: Wild Hunt | 40−45
−1229%
|
545
+1229%
|
| Valorant | 120−130
−270%
|
450−500
+270%
|
Full HD
Ultra Preset
| Battlefield 5 | 65−70
−192%
|
190−200
+192%
|
| Counter-Strike 2 | 27−30
−663%
|
206
+663%
|
| Cyberpunk 2077 | 30−35
−568%
|
207
+568%
|
| Dota 2 | 90−95
−89.4%
|
178
+89.4%
|
| Far Cry 5 | 50−55
−271%
|
189
+271%
|
| Forza Horizon 4 | 60−65
−368%
|
295
+368%
|
| Forza Horizon 5 | 40−45
−388%
|
200−210
+388%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 55−60
−222%
|
170−180
+222%
|
| The Witcher 3: Wild Hunt | 40−45
−627%
|
298
+627%
|
| Valorant | 120−130
−270%
|
450−500
+270%
|
Full HD
Epic Preset
| Fortnite | 80−85
−260%
|
300−350
+260%
|
1440p
High Preset
| Counter-Strike 2 | 16−18
−441%
|
90−95
+441%
|
| Counter-Strike: Global Offensive | 110−120
−365%
|
500−550
+365%
|
| Grand Theft Auto V | 24−27
−588%
|
165
+588%
|
| Metro Exodus | 18−20
−747%
|
161
+747%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 140−150
−19.9%
|
170−180
+19.9%
|
| Valorant | 150−160
−217%
|
450−500
+217%
|
1440p
Ultra Preset
| Battlefield 5 | 40−45
−367%
|
190−200
+367%
|
| Cyberpunk 2077 | 12−14
−1023%
|
146
+1023%
|
| Far Cry 5 | 30−35
−467%
|
187
+467%
|
| Forza Horizon 4 | 35−40
−684%
|
290
+684%
|
| Forza Horizon 5 | 27−30
−381%
|
130−140
+381%
|
| The Witcher 3: Wild Hunt | 24−27
−908%
|
242
+908%
|
1440p
Epic Preset
| Fortnite | 30−35
−358%
|
150−160
+358%
|
4K
High Preset
| Atomic Heart | 12−14
−525%
|
75−80
+525%
|
| Counter-Strike 2 | 7−8
−800%
|
60−65
+800%
|
| Grand Theft Auto V | 27−30
−564%
|
186
+564%
|
| Metro Exodus | 10−12
−882%
|
108
+882%
|
| The Witcher 3: Wild Hunt | 21−24
−852%
|
200
+852%
|
| Valorant | 80−85
−300%
|
300−350
+300%
|
4K
Ultra Preset
| Battlefield 5 | 21−24
−518%
|
130−140
+518%
|
| Counter-Strike 2 | 7−8
−686%
|
55
+686%
|
| Cyberpunk 2077 | 6−7
−1117%
|
73
+1117%
|
| Dota 2 | 50−55
−200%
|
159
+200%
|
| Far Cry 5 | 16−18
−894%
|
159
+894%
|
| Forza Horizon 4 | 24−27
−773%
|
227
+773%
|
| Forza Horizon 5 | 12−14
−400%
|
65−70
+400%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 14−16
−586%
|
95−100
+586%
|
4K
Epic Preset
| Fortnite | 14−16
−427%
|
75−80
+427%
|
This is how HD 7970M Crossfire and RX 7900 XTX compete in popular games:
- RX 7900 XTX is 392% faster in 900p
- RX 7900 XTX is 138% faster in 1080p
- RX 7900 XTX is 447% faster in 1440p
- RX 7900 XTX is 461% faster in 4K
Here's the range of performance differences observed across popular games:
- in The Witcher 3: Wild Hunt, with 1080p resolution and the High Preset, the RX 7900 XTX is 1229% faster.
All in all, in popular games:
- Without exception, RX 7900 XTX surpassed HD 7970M Crossfire in all 64 of our tests.
Pros & cons summary
| Performance score | 16.03 | 80.80 |
| Recency | 1 May 2012 | 3 November 2022 |
| Chip lithography | 28 nm | 5 nm |
| Power consumption (TDP) | 200 Watt | 355 Watt |
HD 7970M Crossfire has 77.5% lower power consumption.
RX 7900 XTX, on the other hand, has a 404.1% higher aggregate performance score, an age advantage of 10 years, and a 460% more advanced lithography process.
The Radeon RX 7900 XTX is our recommended choice as it beats the Radeon HD 7970M Crossfire in performance tests.
Be aware that Radeon HD 7970M Crossfire is a notebook card while Radeon RX 7900 XTX 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.
