RTX4090m Graphics Card
RTX4090m 16GD6 3PH is a flagship PCIe graphics card built on NVIDIA Ada Lovelace architecture. It comes with 16GB GDDR6 video memory and 9728 CUDA Cores. Featuring an ATX 2-slot design and multi-channel 8K output via 3 × DP plus HDMI 2.1, it delivers extreme computing power for high-end workstations and AI inference platforms.
Product Features
- NVIDIA Ada Lovelace architecture, NVIDIA GeForce RTX4090 Max-Q GPU
- 16GB GDDR6 256-bit video memory with 576GB/s memory bandwidth
- 9728 CUDA Cores, 304 Tensor Cores, 76 RT Cores
- PCIe 4.0 x16 full-speed interface
- ATX / 2-Slot form factor (267×111×42mm)
- 3 × DisplayPort 1.4a + 1 × HDMI 2.1 outputs, supports 8K@60Hz
- TDP 150W (240W max), 1×8-pin external power supply
- Supports Windows 10/11 and Linux 64-bit
RTX4090m 16GD6 3PH is powered by the NVIDIA GeForce RTX4090 Max-Q GPU built on the Ada Lovelace architecture. It features 9728 CUDA Cores, 304 Tensor Cores and 76 RT Cores, delivering up to 44.5 TFLOPS of single-precision computing power, making it a performance flagship among PCIe graphics cards. With 16GB GDDR6 256-bit video memory and 576GB/s memory bandwidth, it effortlessly handles large game engines, 8K post-production and complex AI inference workloads.
It adopts the ATX / 2-Slot form factor (267×111×42mm) and PCIe 4.0 x16 bus. It provides 3 × DisplayPort 1.4a and 1 × HDMI 2.1 outputs, all supporting 7680×4320@60Hz. TDP is 150W (240W max), requiring 1×8-pin external power supply. It supports Windows 10/11 and Linux 64-bit, with an operating temperature range of 0~45°C. Suitable for high-end gaming rigs, professional visualization workstations and high-performance edge AI compute nodes.
| Model | RTX4090m 16GD6 3PH (FA11) |
| Product Type | Flagship PCIe GPU |
| GPU Architecture | NVIDIA Ada Lovelace |
| GPU Model | NVIDIA GeForce RTX4090 Max-Q |
| VARM Capacity | 16GB |
| VARM Type | GDDR6 |
| VARM Bus Width | 256bit |
| VARM Bandwidth | 576GB/s |
| Core Clock | 1620MHz（Boost 2040MHz） |
| VARM Clock | 2250MHz |
| CUDA Core | 9728 |
| Tensor Core | 304 |
| RT Core | 76 |
| TMUs | 304 |
| ROPs | 112 |
| SM Count | 76 |
| L1 Cache | 128KB（per SM） |
| L2 Cache | 64MB |
| PCIe Interface | PCI Express 4.0 x16（By 16x） |
| Form Factor | ATX / 2Slot |
| Size | 267 × 111 × 42mm |
| Display Outputs | 3×DisplayPort 1.4a + 1×HDMI2.1 |
| Max Resolution | 7680×4320@60Hz（DP/HDMI） |
| Max Displays | 4 |
| TDP | 150W(240W Max) |
| External Power | 1×8Pin |
| Pixel Fill Rate | 163.0 GPixel/s |
| Texture Fill Rate | 442.3 GTexel/s |
| Single Precision | 44.5 TFLOPS |
| Double Precision | 706.1 GFLOPS |
| DirectX | 12 Ultimate (12_2) |
| OpenGL | 4.6 |
| OpenCL | 3.0 |
| Vulkan | 1.3 |
| Shader Model | 6.7 |
| CUDA Version | 8.9 |
| Operating System | Windows 10 64bit、Windows 11、Linux 64bit |
| Operating Temperature | 0°C ~ 45°C |
| Storage Temperature | -20°C ~ 75°C |
| Operating Humidity | 0%~95%(Non-condensing) |
| Storage Humidity | 10%~90% |
Model: RTX4090m 16GD6 3PH (FA11) | Video Memory: 16GB GDDR6 256-bit | Form Factor: ATX / 2-Slot, 267×111×42mm | Power Consumption: 150W (240W Max) | Interface: PCIe 4.0 x16 | Outputs: 3×DP 1.4a + HDMI 2.1
Technical Documentation
Contact Us
- Get A Quote
- mkt@zrt-tech.com
- 400-838-6869
- 21st Floor, Tower A, Country Garden Phoenix Intelligent Valley, Baoan District, Shenzhen
FAQ
Answers to common questions about this product. For further details, contact our technical support team.
Can't find the answer you need? Our team is happy to help with product selection and customization.