Product overviewMMA5000B6-16G V2 is a compact MXM 3.1 Type B graphics module based on the NVIDIA Ampere architecture. It integrates an NVIDIA Quadro A5000 Max‑Q GPU with 6144 CUDA cores and 16GB GDDR6, delivering sustained professional graphics and AI inference performance for embedded and industrial systems.
Key features- NVIDIA Ampere architecture with NVIDIA Quadro A5000 Max‑Q GPU
- 16GB GDDR6, 256-bit memory bus, 448 GB/s memory bandwidth
- 6144 CUDA cores, 192 Tensor Cores, 48 RT Cores
- MXM 3.1 Type B form factor (105 × 82 mm), PCIe 4.0 x16 interface
- Multiple display outputs: DP 1.4++ and HDMI 2.1 — up to 8K
- TDP options: 82W / 110W / 130W
- Supports Windows 10/11 and major Linux distributions
Technical specificationsModel: MMA5000B6-16G V2
GPU Architecture: NVIDIA Ampere
GPU Model: NVIDIA Quadro A5000 Max‑Q
Memory Capacity: 16GB
Memory Type: GDDR6
Memory Bus Width: 256 bit
Memory Bandwidth: 448 GB/s
Core Frequency (Base/Boost): 900 / 1575 MHz
CUDA Cores: 6144
Tensor Cores: 192
RT Cores: 48
TMUs: 192
ROPs: 96
SM Count: 46
PCIe Interface: PCI Express 4.0 x16
MXM Specification: MXM 3.1 Type B (105 × 82 mm)
TDP: 110W (optional 82W / 130W)
Display Outputs: 2× DP 1.4++ + HDMI 2.1 + DP 1.4++
Maximum Resolution: DP: 7680×4320 @ 120Hz / HDMI: 8K @ 60Hz
Compute: FP32 17.2 TFLOPS, FP64 344.8 GFLOPS
APIs: DirectX 12 Ultimate, OpenGL 4.6, OpenCL 3.0, Vulkan 1.3
Cuda Version: 8.6
Recommended applications- Professional embedded graphics for industrial machines and HMI
- Edge AI inference and accelerated compute in constrained form factors
- 3D visualization, CAD/CAM, simulation and VR/AR workstations
- Imaging, medical visualization and inspection systems
Compatibility & environmentalOperating Systems: Windows 10/11 64-bit, Linux
Operating Temperature: 0°C ~ 45°C
Storage Temperature: -20°C ~ 75°C
Operating Humidity: 0% ~ 95% (non-condensing)
Power Input: DC 12 ~ 19V, 3.3V & 5V ±5%
Ordering: available TDP variants and custom thermal options on request