GeForce RTX 3070 Ti vs GeForce4 440 Go
Aggregate performance score
We've compared GeForce4 440 Go with GeForce RTX 3070 Ti, including specs and performance data.
RTX 3070 Ti outperforms GeForce4 440 Go by a whopping 556000% 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 | 1610 | 52 |
| Place by popularity | not in top-100 | 69 |
| Cost-effectiveness evaluation | no data | 42.95 |
| Power efficiency | no data | 14.86 |
| Architecture | Celsius (1999−2005) | Ampere (2020−2025) |
| GPU code name | NV17 A5 | GA104 |
| Market segment | Laptop | Desktop |
| Release date | 6 February 2002 (24 years ago) | 31 May 2021 (5 years 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
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 | 2 | 6144 |
| Core clock speed | 220 MHz | 1575 MHz |
| Boost clock speed | 220 MHz | 1770 MHz |
| Number of transistors | 29 million | 17,400 million |
| Manufacturing process technology | 150 nm | 8 nm |
| Power consumption (TDP) | no data | 290 Watt |
| Texture fill rate | 0.88 | 339.8 |
| Floating-point processing power | no data | 21.75 TFLOPS |
| ROPs | 2 | 96 |
| TMUs | 4 | 192 |
| Tensor Cores | no data | 192 |
| Ray Tracing Cores | no data | 48 |
| L1 Cache | no data | 6 MB |
| L2 Cache | no data | 4 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).
| Interface | AGP 4x | PCIe 4.0 x16 |
| Length | no data | 267 mm |
| Width | no data | 2-slot |
| Supplementary power connectors | no data | 1x 12-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 | DDR | GDDR6X |
| Maximum RAM amount | 64 MB | 8 GB |
| Memory bus width | 128 Bit | 256 Bit |
| Memory clock speed | 220 MHz | 1188 MHz |
| Memory bandwidth | 7.04 GB/s | 608.3 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, 3x DisplayPort |
| HDMI | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 8.0 | 12 Ultimate (12_2) |
| Shader Model | no data | 6.6 |
| OpenGL | 1.3 | 4.6 |
| OpenCL | N/A | 3.0 |
| Vulkan | N/A | 1.2 |
| CUDA | - | 8.6 |
| 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.
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 | -0−1 | 161 |
| 1440p | -0−1 | 86 |
| 4K | -0−1 | 57 |
Cost per frame, $
| 1080p | no data | 3.72 |
| 1440p | no data | 6.97 |
| 4K | no data | 10.51 |
FPS performance in popular games
Full HD
Low
| Atomic Heart | 0−1 | 170−180 |
Full HD
Medium
| Atomic Heart | 0−1 | 170−180 |
| Forza Horizon 4 | 2−3 | 210−220
+10700%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 7−8 | 170−180
+2371%
|
| Valorant | 24−27 | 300−350
+1131%
|
Full HD
High
| Atomic Heart | 0−1 | 170−180 |
| Counter-Strike: Global Offensive | 9−10 | 270−280
+2989%
|
| Dota 2 | 7−8 | 249
+3457%
|
| Forza Horizon 4 | 2−3 | 210−220
+10700%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 7−8 | 170−180
+2371%
|
| The Witcher 3: Wild Hunt | 5−6 | 294
+5780%
|
| Valorant | 24−27 | 300−350
+1131%
|
Full HD
Ultra
| Dota 2 | 7−8 | 230
+3186%
|
| Forza Horizon 4 | 2−3 | 210−220
+10700%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 7−8 | 170−180
+2371%
|
| The Witcher 3: Wild Hunt | 5−6 | 144
+2780%
|
| Valorant | 24−27 | 300−350
+1131%
|
1440p
High
| Counter-Strike 2 | 1−2 | 160
+15900%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 0−1 | 170−180 |
1440p
Ultra
| The Witcher 3: Wild Hunt | 1−2 | 113
+11200%
|
4K
High
| Grand Theft Auto V | 14−16 | 147
+950%
|
| Valorant | 4−5 | 300−350
+7725%
|
4K
Ultra
| PLAYERUNKNOWN'S BATTLEGROUNDS | 1−2 | 95−100
+9500%
|
4K
Epic
| Fortnite | 1−2 | 75−80
+7800%
|
Full HD
Low
| Counter-Strike 2 | 350 | 350 |
| Cyberpunk 2077 | 178 | 178 |
| Resident Evil 4 Remake | 219 | 219 |
Full HD
Medium
| Battlefield 5 | 160−170 | 160−170 |
| Counter-Strike 2 | 337 | 337 |
| Cyberpunk 2077 | 141 | 141 |
| Far Cry 5 | 205 | 205 |
| Fortnite | 250−260 | 250−260 |
Full HD
High
| Battlefield 5 | 160−170 | 160−170 |
| Counter-Strike 2 | 266 | 266 |
| Cyberpunk 2077 | 124 | 124 |
| Far Cry 5 | 196 | 196 |
| Fortnite | 250−260 | 250−260 |
| Grand Theft Auto V | 173 | 173 |
| Metro Exodus | 145 | 145 |
Full HD
Ultra
| Battlefield 5 | 160−170 | 160−170 |
| Cyberpunk 2077 | 113 | 113 |
| Far Cry 5 | 183 | 183 |
Full HD
Epic
| Fortnite | 250−260 | 250−260 |
1440p
High
| Counter-Strike: Global Offensive | 400−450 | 400−450 |
| Grand Theft Auto V | 137 | 137 |
| Metro Exodus | 89 | 89 |
| Valorant | 350−400 | 350−400 |
1440p
Ultra
| Battlefield 5 | 130−140 | 130−140 |
| Cyberpunk 2077 | 73 | 73 |
| Far Cry 5 | 150 | 150 |
| Forza Horizon 4 | 170−180 | 170−180 |
1440p
Epic
| Fortnite | 150−160 | 150−160 |
4K
High
| Atomic Heart | 45−50 | 45−50 |
| Counter-Strike 2 | 47 | 47 |
| Metro Exodus | 56 | 56 |
| The Witcher 3: Wild Hunt | 109 | 109 |
4K
Ultra
| Battlefield 5 | 95−100 | 95−100 |
| Counter-Strike 2 | 70−75 | 70−75 |
| Cyberpunk 2077 | 35 | 35 |
| Dota 2 | 194 | 194 |
| Far Cry 5 | 82 | 82 |
| Forza Horizon 4 | 120−130 | 120−130 |
Here's the range of performance differences observed across popular games:
- in Counter-Strike 2, with 1440p resolution and the High Preset, the RTX 3070 Ti is 15900% faster.
All in all, in popular games:
- RTX 3070 Ti performs better in 20 tests (34%)
- there's a draw in 38 tests (66%)
Pros & cons summary
| Performance score | 0.01 | 55.61 |
| Recency | 6 February 2002 | 31 May 2021 |
| Maximum RAM amount | 64 MB | 8 GB |
| Chip lithography | 150 nm | 8 nm |
RTX 3070 Ti has a 556000% higher aggregate performance score, an age advantage of 19 years, a 12700% higher maximum VRAM amount, and a 95% more advanced lithography process.
The GeForce RTX 3070 Ti is our recommended choice as it beats the GeForce4 440 Go in performance tests.
Be aware that GeForce4 440 Go is a notebook graphics card while GeForce RTX 3070 Ti 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.
