AMD Radeon Instinct MI25 vs NVIDIA Quadro K4200
Graphics Processor
| GPU model | Vega 10 | GK104 |
|---|---|---|
| GPU variant | Vega 10 XT GL (215-0894124) | GK104-850-A2 |
| Architecture | GCN 5.0 | Kepler |
| Foundry | GlobalFoundries | TSMC |
| Manufacturing process | 14 nm | 28 nm |
| Number of transistors | 12,500 million | 3,540 million |
| Die size | 495 mm² | 294 mm² |
Graphics Card
| Release date | Jun 27th, 2017 | Jul 22nd, 2014 |
|---|---|---|
| Generation | Radeon Instinct | Quadro |
| Production | Active | End-of-life |
| Interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
| Reviews | — | 26 in our database |
Clocks
| Base clock | 1400 MHz | 771 MHz |
|---|---|---|
| Boost clock | 1500 MHz | 784 MHz |
| Memory clock | 852 MHz 1704 Mbps effective | 1350 MHz 5.4 Gbps effective |
Memory Configuration
| Memory size | 16 GB | 4 GB |
|---|---|---|
| Memory type | HBM2 | GDDR5 |
| Memory bus width | 2048 bit | 256 bit |
| Bandwidth | 436.2 GB/s | 172.8 GB/s |
Render Configuration
| Shading units | 4096 | 1344 |
|---|---|---|
| TMUs | 256 | 112 |
| ROPs | 64 | 32 |
| Compute units | 64 | — |
| Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
| Cache L2 | 4 MB | 512 KB |
| SMX count | — | 7 |
Performance
| Pixel rate | 96.00 GPixel/s | 21.95 GPixel/s |
|---|---|---|
| Texture rate | 384.0 GTexel/s | 87.81 GTexel/s |
| FP16 (half) performance | 24.58 TFLOPS (2:1) | — |
| FP32 (float) performance | 12.29 TFLOPS | 2.107 TFLOPS |
| FP64 (double) performance | 768.0 GFLOPS (1:16) | 87.81 GFLOPS (1:24) |
Dimensions & Outputs
| Slot width | Dual-slot | Single-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | 241 mm 9.5 inches |
| Width | 111 mm 4.4 inches | 111 mm 4.4 inches |
| TDP | 300 W | 108 W |
| Suggested PSU | 700 W | 300 W |
| Outputs | No outputs | 1x DVI2x DisplayPort |
| Power connectors | 2x 8-pin | 1x 6-pin |
| Board number | D051 | P2004 |
API Support & Features
| DirectX | 12 (12_1) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.4 | 5.1 |
| CUDA | — | 3.0 |
