GeForce RTX 3090 Ti vs Radeon HD 6950M
Aggregate performance score
We've compared Radeon HD 6950M with GeForce RTX 3090 Ti, including specs and performance data.
RTX 3090 Ti outperforms HD 6950M by a whopping 2053% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 723 | 10 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 8.17 |
| Power efficiency | 4.93 | 11.79 |
| Architecture | TeraScale 2 (2009−2015) | Ampere (2020−2024) |
| GPU code name | Blackcomb | GA102 |
| Market segment | Laptop | Desktop |
| Release date | 4 January 2011 (14 years ago) | 27 January 2022 (2 years ago) |
| Launch price (MSRP) | no data | $1,999 |
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 | 960 | 10752 |
| Core clock speed | 580 MHz | 1560 MHz |
| Boost clock speed | no data | 1860 MHz |
| Number of transistors | 1,700 million | 28,300 million |
| Manufacturing process technology | 40 nm | 8 nm |
| Power consumption (TDP) | 50 Watt | 450 Watt |
| Texture fill rate | 27.84 | 625.0 |
| Floating-point processing power | 1.114 TFLOPS | 40 TFLOPS |
| ROPs | 32 | 112 |
| TMUs | 48 | 336 |
| Tensor Cores | no data | 336 |
| Ray Tracing Cores | no data | 84 |
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 | MXM-B (3.0) | PCIe 4.0 x16 |
| Length | no data | 336 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 | GDDR5 | GDDR6X |
| Maximum RAM amount | 1 GB | 24 GB |
| Memory bus width | 256 Bit | 384 Bit |
| Memory clock speed | 900 MHz | 1313 MHz |
| Memory bandwidth | 115.2 GB/s | 1,008 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 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 | 6.6 |
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | - | 8.6 |
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.
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.
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 | 10−12
−2100%
| 220
+2100%
|
| 1440p | 7−8
−2086%
| 153
+2086%
|
| 4K | 5−6
−2060%
| 108
+2060%
|
Cost per frame, $
| 1080p | no data | 9.09 |
| 1440p | no data | 13.07 |
| 4K | no data | 18.51 |
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 10−12
−1545%
|
180−190
+1545%
|
| Cyberpunk 2077 | 8−9
−2638%
|
219
+2638%
|
| Elden Ring | 8−9
−3688%
|
300−350
+3688%
|
Full HD
Medium Preset
| Battlefield 5 | 10−11
−1070%
|
110−120
+1070%
|
| Counter-Strike 2 | 10−12
−1545%
|
180−190
+1545%
|
| Cyberpunk 2077 | 8−9
−1163%
|
101
+1163%
|
| Forza Horizon 4 | 16−18
−2656%
|
400−450
+2656%
|
| Metro Exodus | 7−8
−2071%
|
150−160
+2071%
|
| Red Dead Redemption 2 | 12−14
−1083%
|
140−150
+1083%
|
| Valorant | 4−5
−10525%
|
400−450
+10525%
|
Full HD
High Preset
| Battlefield 5 | 10−11
−1070%
|
110−120
+1070%
|
| Counter-Strike 2 | 10−12
−1545%
|
180−190
+1545%
|
| Cyberpunk 2077 | 8−9
−975%
|
86
+975%
|
| Dota 2 | 10−12
−1582%
|
185
+1582%
|
| Elden Ring | 8−9
−3863%
|
317
+3863%
|
| Far Cry 5 | 18−20
−616%
|
136
+616%
|
| Fortnite | 20−22
−1440%
|
300−350
+1440%
|
| Forza Horizon 4 | 16−18
−2656%
|
400−450
+2656%
|
| Grand Theft Auto V | 10−12
−1445%
|
170
+1445%
|
| Metro Exodus | 7−8
−943%
|
73
+943%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 30−35
−572%
|
210−220
+572%
|
| Red Dead Redemption 2 | 12−14
−1083%
|
140−150
+1083%
|
| The Witcher 3: Wild Hunt | 12−14
−1238%
|
170−180
+1238%
|
| Valorant | 4−5
−10525%
|
400−450
+10525%
|
| World of Tanks | 60−65
−350%
|
270−280
+350%
|
Full HD
Ultra Preset
| Battlefield 5 | 10−11
−1070%
|
110−120
+1070%
|
| Counter-Strike 2 | 10−12
−1545%
|
180−190
+1545%
|
| Cyberpunk 2077 | 8−9
−850%
|
76
+850%
|
| Dota 2 | 10−12
−1673%
|
195
+1673%
|
| Far Cry 5 | 18−20
−663%
|
140−150
+663%
|
| Forza Horizon 4 | 16−18
−2656%
|
400−450
+2656%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 30−35
−572%
|
210−220
+572%
|
| Valorant | 4−5
−10525%
|
400−450
+10525%
|
1440p
High Preset
| Dota 2 | 1−2
−15000%
|
151
+15000%
|
| Elden Ring | 3−4
−6833%
|
208
+6833%
|
| Grand Theft Auto V | 2−3
−7450%
|
151
+7450%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
−600%
|
170−180
+600%
|
| Red Dead Redemption 2 | 2−3
−4550%
|
90−95
+4550%
|
| World of Tanks | 24−27
−1964%
|
500−550
+1964%
|
1440p
Ultra Preset
| Battlefield 5 | 4−5
−2075%
|
85−90
+2075%
|
| Counter-Strike 2 | 9−10
−1089%
|
100−110
+1089%
|
| Cyberpunk 2077 | 3−4
−1633%
|
52
+1633%
|
| Far Cry 5 | 8−9
−1900%
|
160−170
+1900%
|
| Forza Horizon 4 | 3−4
−9900%
|
300−310
+9900%
|
| The Witcher 3: Wild Hunt | 5−6
−3460%
|
170−180
+3460%
|
| Valorant | 10−12
−3173%
|
350−400
+3173%
|
4K
High Preset
| Dota 2 | 16−18
−1031%
|
181
+1031%
|
| Elden Ring | 1−2
−11500%
|
116
+11500%
|
| Grand Theft Auto V | 16−18
−1031%
|
181
+1031%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 10−11
−1990%
|
200−210
+1990%
|
| Red Dead Redemption 2 | 2−3
−3100%
|
60−65
+3100%
|
| The Witcher 3: Wild Hunt | 16−18
−1031%
|
181
+1031%
|
4K
Ultra Preset
| Battlefield 5 | 3−4
−2933%
|
90−95
+2933%
|
| Cyberpunk 2077 | 1−2
−2600%
|
27
+2600%
|
| Dota 2 | 16−18
−1050%
|
184
+1050%
|
| Far Cry 5 | 4−5
−2525%
|
100−110
+2525%
|
| Fortnite | 2−3
−4700%
|
95−100
+4700%
|
| Forza Horizon 4 | 1−2
−16200%
|
160−170
+16200%
|
| Valorant | 3−4
−6900%
|
210−220
+6900%
|
1440p
Ultra Preset
| Metro Exodus | 130−140
+0%
|
130−140
+0%
|
4K
High Preset
| Counter-Strike 2 | 100−105
+0%
|
100−105
+0%
|
| Metro Exodus | 84
+0%
|
84
+0%
|
4K
Ultra Preset
| Counter-Strike 2 | 100−105
+0%
|
100−105
+0%
|
This is how HD 6950M and RTX 3090 Ti compete in popular games:
- RTX 3090 Ti is 2100% faster in 1080p
- RTX 3090 Ti is 2086% faster in 1440p
- RTX 3090 Ti is 2060% faster in 4K
Here's the range of performance differences observed across popular games:
- in Forza Horizon 4, with 4K resolution and the Ultra Preset, the RTX 3090 Ti is 16200% faster.
All in all, in popular games:
- RTX 3090 Ti is ahead in 59 tests (94%)
- there's a draw in 4 tests (6%)
Pros & cons summary
| Performance score | 3.58 | 77.06 |
| Recency | 4 January 2011 | 27 January 2022 |
| Maximum RAM amount | 1 GB | 24 GB |
| Chip lithography | 40 nm | 8 nm |
| Power consumption (TDP) | 50 Watt | 450 Watt |
HD 6950M has 800% lower power consumption.
RTX 3090 Ti, on the other hand, has a 2052.5% higher aggregate performance score, an age advantage of 11 years, a 2300% higher maximum VRAM amount, and a 400% more advanced lithography process.
The GeForce RTX 3090 Ti is our recommended choice as it beats the Radeon HD 6950M in performance tests.
Be aware that Radeon HD 6950M is a notebook card while GeForce RTX 3090 Ti 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.
