RTX 2070
RTX 2070 Review & Specifications
The RTX 2070 is based on the Turing architecture and manufactured using the 12 nm nm process node. It was launched approximately 7 years, 9 months ago, originally priced at $499. It features 2304 cores, including 72 compute units (SMs), 144 texture mapping units (TMUs), and 64 render output units (ROPs). For ray tracing and AI-accelerated tasks, it also includes 36 dedicated RT cores and 288 Tensor cores, enabling advanced rendering and upscaling features where supported. It has a base clock of 1410 MHz and a boost clock reaching up to 1620 MHz. The RTX 2070 comes equipped with 8 GB of GDDR6 memory across a 256-bit bus. Memory runs at 1750 MHz and delivers a total memory bandwidth of 448 GB/s.
This GPU has a low thermal design power (TDP) of 175 W. It is generally compatible with almost all PC cases and is excellent for SFF and compact systems where heat dissipation is a concern.
RTX 2070 Performance
RTX 2070 is an entry-level graphics card with a relative gaming performance score of 26.92%. It performs well at 1080p and can handle 1440p with optimized settings or features like DLSS and FSR, though it's not suitable for 4K. Intended for for casual gamers or users who play occasionally on general-purpose PCs.
The RTX 2070 offers 8 GB of VRAM — a reasonable amount for its class. It performs well in 1080p gaming and modest 1440p workloads, though its lower compute performance may limit use of advanced settings or ray tracing. With support for DLSS, NVIDIA users can extend playability at higher resolutions. In creative tasks like photo editing or Full HD video, the GPU is adequate. Thanks to the NVIDIA ecosystem, this GPU is capable of basic AI experimentation, including inference with smaller models or quantized architectures — a good entry-level solution for developers interested in ML.
With a 59.3% performance-per-price ratio, RTX 2070 offers reasonable value. It's a viable choice for budget-conscious users, though limited VRAM and lower performance restrict its lifespan.
General Information
| GPU Name | RTX 2070 |
|---|---|
| GPU Code Name | TU106 |
| Release Price | $499 |
| Selected Model | ASUS ROG STRIX GeForce RTX 2070 SUPER Advanced Overclocked 8G GDDR6 HDMI DisplayPort USB Type-C Gaming Graphics Card (ROG-STRIX-RTX-2070S-A8G-GAMING) (Renewed) |
| Current Price Amazon | $350 |
| Amazon Price Updated | 1 week, 4 days ago |
| Launch Date | 7 years, 9 months ago |
| GPU Available | True |
| Architecture | Turing |
|---|---|
| Foundry | TSMC |
| Process | 12 nm |
| Transistors | 10800 million |
| Die Size | 445 mm² |
| Bus Interface | PCIe 3.0 x16 |
| TDP | 175 W |
| Cores | 2304 |
|---|---|
| CUs (SMs) | 72 |
| TMUs | 144 |
| ROPs | 64 |
| RT Cores | 36 |
| Tensor Cores | 288 |
| L1 Cache | 64 KB (per SM) |
| L2 Cache | 4 MB |
| Base Clock | 1410 MHz |
|---|---|
| Boost Clock | 1620 MHz |
| Memory Size - Type | 8 GB GDDR6 |
|---|---|
| Memory Bus Width | 256 bit |
| Memory Clock | 1750 MHz |
| Memory Bandwidth | 448 GB/s |
| DirectX | 12 Ultimate (12_2) |
|---|---|
| OpenGL | 4.6 |
| OpenCL | 3.0 |
| Vulkan | 1.4 |
| Shader Model | 6.8 |
Theoretical Performance
| Pixel Rate | 288.00 GPixel/s |
|---|---|
| Texture Rate | 233.30 GTexel/s |
| FP16 | 14.93 TFLOPS |
| FP32 | 7.47 TFLOPS |
| FP64 | 233.31 GFLOPS |
Gaming Performance Chart
RTX 2070 Compared to Similar Performance GPUs
GPU Price / Performance Table
| GPU (Desc) | Price (Desc) | Gaming_1080p (Desc) | Gaming_1440p (Desc) | Gaming_2160p (Desc) | Game_1440p/Price (Desc) |
|---|---|---|---|---|---|
|
$321
|
0.0%
|
30.2%
|
23.8%
|
18.6%
|
73.4%
|
|
|
$549
|
0.0%
|
28.6%
|
22.6%
|
17.6%
|
40.7%
|
|
|
$285❗
|
0.0%
|
25.9%
|
22.4%
|
17.8%
|
77.9%
|
|
|
$699
|
↑
68.8%
|
26.9%
|
22.3%
|
18.9%
|
31.6%
|
|
|
$350
|
0.0%
|
26.9%
|
21.0%
|
17.9%
|
59.3%
|
|
|
$240❗
|
0.0%
|
26.6%
|
20.7%
|
17.0%
|
85.5%
|
|
|
$200
|
0.0%
|
23.7%
|
19.9%
|
16.8%
|
98.4%
|
|
|
$479
|
↑
50.1%
|
24.5%
|
19.3%
|
14.5%
|
39.8%
|
|
|
$230
|
0.0%
|
21.9%
|
17.4%
|
12.2%
|
75.1%
|
GPU Specification Table
| GPU (Desc) | Architecture | Shader/TMU/ROP/RT | Base/Boost Clock | Memory | Mem Clock/Bandwidth | TDP |
|---|---|---|---|---|---|---|
| RX 7600 | Navi 33 / 6 nm / RDNA 3.0 | 2048 / 128 / 64 / 32 | 1720 MHz / 2655 MHz | 8 GB GDDR6 / 128 bit | 2250 MHz / 288 GB/s | 165 W |
| RX 6600 XT | Navi 23 / 7 nm / RDNA 2.0 | 2048 / 128 / 64 / 32 | 1968 MHz / 2589 MHz | 8 GB GDDR6 / 128 bit | 2000 MHz / 256 GB/s | 160 W |
| Arc A750 | DG2-512 / 6 nm / Xe HPG | 3584 / 224 / 112 / 28 | 2050 MHz / 2400 MHz | 8 GB GDDR6 / 256 bit | 2000 MHz / 512 GB/s | 225 W |
| RTX 3060 12GB | GA106 / 8 nm nm / Ampere | 3584 / 112 / 48 / 28 | 1320 MHz / 1777 MHz | 12 GB GDDR6 / 192 bit | 1875 MHz / 360 GB/s | 170 W |
| RTX 2070 | TU106 / 12 nm nm / Turing | 2304 / 144 / 64 / 36 | 1410 MHz / 1620 MHz | 8 GB GDDR6 / 256 bit | 1750 MHz / 448 GB/s | 175 W |
| RTX 2060 SUPER | TU106 / 12 nm nm / Turing | 2176 / 136 / 64 / 34 | 1470 MHz / 1650 MHz | 8 GB GDDR6 / 256 bit | 1750 MHz / 448 GB/s | 175 W |
| Arc A580 | DG2-512 / 6 nm / Xe HPG | 3072 / 192 / 96 / 24 | 1700 MHz / 2000 MHz | 8 GB GDDR6 / 256 bit | 2000 MHz / 512 GB/s | 175 W |
| RX 6600 | Navi 23 / 7 nm / RDNA 2.0 | 1792 / 112 / 64 / 28 | 1626 MHz / 2491 MHz | 8 GB GDDR6 / 128 bit | 1750 MHz / 224 GB/s | 132 W |
| RTX 2060 | TU106 / 12 nm nm / Turing | 1920 / 120 / 48 / 30 | 1365 MHz / 1680 MHz | 6 GB GDDR6 / 192 bit | 1750 MHz / 336 GB/s | 160 W |
Add Comment on RTX 2070