NVIDIA Quadro RTX 4000 vs NVIDIA T400 4 GB
Graphics Processor
| GPU model | TU104 | TU117 |
|---|---|---|
| GPU variant | TU104-850-A1 | — |
| Architecture | Turing | Turing |
| Foundry | TSMC | TSMC |
| Manufacturing process | 12 nm | 12 nm |
| Number of transistors | 13,600 million | 4,700 million |
| Die size | 545 mm² | 200 mm² |
Graphics Card
| Release date | Nov 13th, 2018 | May 6th, 2021 |
|---|---|---|
| Generation | Quadro | Quadro |
| Production | Active | Active |
| Launch price | 899 USD | — |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Clocks
| Base clock | 1005 MHz | 420 MHz |
|---|---|---|
| Boost clock | 1545 MHz | 1425 MHz |
| Memory clock | 1625 MHz 13 Gbps effective | 1250 MHz 10 Gbps effective |
Memory Configuration
| Memory size | 8 GB | 4 GB |
|---|---|---|
| Memory type | GDDR6 | GDDR6 |
| Memory bus width | 256 bit | 64 bit |
| Bandwidth | 416.0 GB/s | 80.00 GB/s |
Render Configuration
| Shading units | 2304 | 384 |
|---|---|---|
| TMUs | 144 | 24 |
| ROPs | 64 | 16 |
| SM count | 36 | 6 |
| Tensor cores | 288 | — |
| RT cores | 36 | — |
| Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
| Cache L2 | 4 MB | 1024 KB |
Performance
| Pixel rate | 98.88 GPixel/s | 22.80 GPixel/s |
|---|---|---|
| Texture rate | 222.5 GTexel/s | 34.20 GTexel/s |
| FP16 (half) performance | 14.24 TFLOPS (2:1) | 2.189 TFLOPS (2:1) |
| FP32 (float) performance | 7.119 TFLOPS | 1,094 GFLOPS |
| FP64 (double) performance | 222.5 GFLOPS (1:32) | 34.20 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Single-slot | Single-slot |
|---|---|---|
| Length | 241 mm 9.5 inches | — |
| Width | 111 mm 4.4 inches | — |
| TDP | 160 W | 30 W |
| Suggested PSU | 450 W | 200 W |
| Outputs | 3x DisplayPort1x USB Type-C | 3x mini-DisplayPort |
| Power connectors | 1x 8-pin | None |
API Support & Features
| DirectX | 12 Ultimate (12_2) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 7.5 | 7.5 |
| Shader model | 6.6 | 6.6 |
