NVIDIA GeForce GTX 1650 Mobile Refresh vs NVIDIA GeForce RTX 3070 Max-Q
Graphics Processor
| GPU model | TU117B | GA104 |
|---|---|---|
| Architecture | Turing | Ampere |
| Foundry | TSMC | Samsung |
| Manufacturing process | 12 nm | 8 nm |
| Number of transistors | 4,700 million | 17,400 million |
| Die size | 200 mm² | 392 mm² |
| GPU variant | — | GA104-770-A1 |
Mobile graphics
| Release date | Apr 15th, 2020 | Jan 12th, 2021 |
|---|---|---|
| Generation | GeForce 16 Mobile | GeForce 30 Mobile |
| Production | Active | Active |
| Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Reviews | 44 in our database | 1 in our database |
| gpu.details.availability | — | Feb 2nd, 2021 |
| Predecessor | — | GeForce 20 Mobile |
Clocks
| Base clock | 1380 MHz | 780 MHz |
|---|---|---|
| Boost clock | 1515 MHz | 1290 MHz |
| Memory clock | 1500 MHz 12000 MHz effective | 1500 MHz 12 Gbps effective |
Memory Configuration
| Memory size | 4 GB | 8 GB |
|---|---|---|
| Memory type | GDDR6 | GDDR6 |
| Memory bus width | 128 bit | 256 bit |
| Bandwidth | 192.0 GB/s | 384.0 GB/s |
Render Configuration
| Shading units | 1024 | 5120 |
|---|---|---|
| TMUs | 64 | 160 |
| ROPs | 32 | 80 |
| SM count | 16 | 40 |
| Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 1024 KB | 4 MB |
| Tensor cores | — | 160 |
| RT cores | — | 40 |
Performance
| Pixel rate | 48.48 GPixel/s | 103.2 GPixel/s |
|---|---|---|
| Texture rate | 96.96 GTexel/s | 206.4 GTexel/s |
| FP16 (half) performance | 6.205 TFLOPS (2:1) | 13.21 TFLOPS (1:1) |
| FP32 (float) performance | 3.103 TFLOPS | 13.21 TFLOPS |
| FP64 (double) performance | 96.96 GFLOPS (1:32) | 206.4 GFLOPS (1:64) |
Dimensions & Outputs
| TDP | 50 W | 80 W |
|---|---|---|
| Outputs | No outputs | No outputs |
| Power connectors | None | None |
API Support & Features
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | 1.2.140 | 1.2 |
| CUDA | 7.5 | 8.6 |
| Shader model | 6.5 | 6.6 |
