Home » Products » AI Computing Module » RTX4060m 8GD6 PH SFF
RTX4060m PCIe Module
The RTX4060m 8GD6 PH SFF is a cost-effective compact PCIe graphics card built on the NVIDIA Ada Lovelace architecture. Featuring 8GB GDDR6 memory and 3072 CUDA cores, it adopts a 169mm SFF single-slot form factor. With a low 65W power draw and no external power supply required, it is well suited for mainstream small-form embedded graphics applications.
Product Features
- NVIDIA Ada Lovelace Architecture,NVIDIA GeForce RTX4060 Mobility GPU
- 8GB GDDR6 128-bit VRAM with 256GB/s memory bandwidth
- 3072 CUDA Cores,96 Tensor Cores,24 RT Cores
- PCIe 4.0 x8 interface;SFF/1-Slot form factor (169×69×18.7mm)
- 1×DisplayPort 1.4 + 1×HDMI2.1 outputs,supports 8K@60Hz
- TDP 65W,no external power required
RTX4060m 8GD6 PH SFF is equipped with the NVIDIA GeForce RTX 4060 Mobility GPU built on the Ada Lovelace architecture. It features 3072 CUDA cores, 96 Tensor Cores and 24 RT Cores, delivering single-precision floating-point performance of 12.3 TFLOPS. With 8GB GDDR6 128-bit VRAM and 256GB/s memory bandwidth, it smoothly runs mainstream 3D software, HD video processing and lightweight AI inference workloads.
Adopting an ultra-compact SFF / 1-slot form factor (169×69×18.7mm) and PCIe 4.0 x8 bus, it provides 1× DisplayPort 1.4 and 1× HDMI 2.1 outputs, both supporting 7680×4320@60Hz. With a TDP of only 65W and no external power required, it has minimal cooling requirements. Compatible with Windows 10/11 and 64-bit Linux, and operating within a 0~45°C temperature range, it serves as an ideal graphics solution for compact embedded devices including small ITX PCs, industrial all-in-one PCs, digital signage and medical equipment.
| Model | RTX4060m 8GD6 PH SFF (FA17) |
| Model Type | SFF Compact PCIe Graphics Card |
| GPU Architecture | NVIDIA Ada Lovelace |
| GPU Model | NVIDIA GeForce RTX4060 Mobility |
| VARM Capacity | 8GB |
| VARM Type | GDDR6 |
| VARM Bit Width | 128bit |
| Memory Bandwidth | 256GB/s |
| Core Clock | 1140MHz(Boost 1470MHz) |
| Memory Clock | 2000MHz(16.0Gbps) |
| CUDA Core | 3072 |
| Tensor Core | 96 |
| RT Core | 24 |
| TMUs | 96 |
| ROPs | 48 |
| SM Count | 24 |
| L1 Cache | 128KB(per SM) |
| L2 Cache | 32MB |
| PCIe Interface | PCI Express 4.0 x16(By 8x) |
| Board Specs | SFF / 1Slot |
| Size | 169 × 69 × 18.7mm |
| Display Outputs | 1×DisplayPort 1.4 + 1×HDMI2.1 |
| Max Resolution | 7680×4320@60Hz(DP/HDMI) |
| Max Displays | 2 |
| TDP Power | 65W |
| External Power | N/A(No External Power Required) |
| Pixel Fill Rate | 70.56 GPixel/s |
| Texture Fill Rate | 141.1 GTexel/s |
| Single Precision FP32 | 12.3 TFLOPS |
| Double Precision FP64 | 221.5 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 11、Windows 10 64bit、Linux 64bit |
| Operaiting Temperature | 0°C ~ 45°C |
| Storage Temperature | -20°C ~ 75°C |
| Operation Humidity | 0%~95%(Non-condensing) |
| Storge Humidity | 10%~90% |
Model:RTX4060m 8GD6 PH SFF (FA17) | VARM:8GB GDDR6 128bit | Form Factor:SFF/1Slot 169×69×18.7mm | Power:65W(No Eexternal Power Required) | Interface:PCIe 4.0 x8 | Outputs:1×DP 1.4 + 1×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.