Versus Engine
NVIDIA Vera Rubin NVL72 vs Snapdragon X2 Series
Specs, price and the one trade-off that actually decides it — NVIDIA Vera Rubin NVL72 against Snapdragon X2 Series, side by side.
Cheaper to start
Tie
Both start at a similar price.
Best ecosystem
Tie
Neither lists native integrations.
Standout
NVIDIA Vera Rubin NVL72
72 NVIDIA Rubin GPUs and 36 NVIDIA Vera CPUs
NVIDIA Vera Rubin NVL72
High-performance computing system with 72 NVIDIA Rubin GPUs and 36 NVIDIA Vera CPUs.
Where it wins, where it doesn't
Pros
- Offers up to 9,360 TFLOPS FP32 and 288 PFLOPS FP16/BF16 for high-performance computing.
- Equipped with up to 54 TB of LPDDR5X CPU memory, ensuring ample resources for complex tasks.
- Supports up to 20.7 TB HBM4 GPU memory with 1,400 TB/s bandwidth, ideal for data-intensive applications.
Cons
- High power consumption and cooling requirements make it unsuitable for environments without robust infrastructure.
- Limited networking bandwidth in smaller configurations restricts scalability and flexibility.
- Complex NVLink requirements necessitate a specific setup, complicating deployment and maintenance.
Specifications
- APIs—
- Architecture—
- Cache Capacity—
- Clock Speed—
- Configuration72 NVIDIA Rubin GPUs | 36 NVIDIA Vera CPUs | 2 NVIDIA Rubin GPUs | 1 NVIDIA Vera CPU | 1 NVIDIA Rubin GPU
- Connectivity—
- CPU Core Count3,168 custom NVIDIA Olympus cores | 6,336 Threads | 88 custom NVIDIA Olympus cores | 176 Threads | -
- CPU MemoryUp to 54 TB LPDDR5X | Up to 1.5 TB LPDDR5X | -
- CPU Name—
- Display Support—
- FP16/BF16³288 PFLOPS | 8 PFLOPS | 4 PFLOPS
- FP329,360 TFLOPS | 260 TFLOPS | 130 TFLOPS
- FP642,400 TFLOPS | 67 TFLOPS | 33 TFLOPS
- FP8/FP6 Training³1,260 PFLOPS | 35 PFLOPS | 17.5 PFLOPS
- GPU Clock Speed—
- GPU Memory | Bandwidth20.7 TB HBM4 | 1,400 TB/s | 576 GB HBM4 | 38.5 TB/s | 288 GB HBM4 | 19.2 TB/s
- GPU Name—
- GPU Part Number—
- GPUs in 100 MW¹40K GPUs
- Inlet Temp45°C
- Memory Bandwidth—
- Memory Type—
- Networking Bandwidth (Scale-Out)´32.4 TB/s | 0.9 TB/s | 0.45 TB/s
- npu—
- NPU Name—
- NPU Tera Operations Per Second—
- Number of Cores—
- NVFP4 Inference²3,600 PFLOPS | 100 PFLOPS | 50 PFLOPS
- NVFP4 Training³2,520 PFLOPS | 70 PFLOPS | 35 PFLOPS
- NVIDIA NVLinkSixth Generation
- NVLink Bandwidth216 TB/s | 6 TB/s | 3 TB/s
- NVLink-C2C Bandwidth65 TB/s | 1.8 TB/s | -
- Part Number—
- Storage Connection—
- Storage Interface—
- TF32³144 PFLOPS | 4 PFLOPS | 2 PFLOPS
- Total NVIDIA + HBM4 Chips1,296 | 30 | 12
- Video Codec Support—
Snapdragon X2 Series
Qualcomm's 2nd-gen PC platform with 41% higher CPU and 2x NPU performance (80 TOPS).
Where it wins, where it doesn't
Pros
- Up to 18 cores and 85 TOPS NPU for high performance.
- Supports up to 5.0 GHz clock speed and 135 GB/s memory bandwidth.
- Advanced display support for up to 3 displays at 4K 144Hz or 5K 60Hz.
Cons
- Limited storage bandwidth of 40 Gbps may restrict high-capacity storage options.
Specifications
- APIsDirectX® 12.2, Vulkan® 1.4, OpenCL™ 3.0
- Architecture64-bit
- Cache CapacityUp to 53 MB
- Clock SpeedUp to 5.0 GHz, Up to 4.4 GHz
- Configuration—
- ConnectivitySnapdragon X2 Elite Extreme
- CPU Core Count—
- CPU Memory—
- CPU NameQualcomm® Oryon™
- Display Support3 displays at up to 4K at 144 Hz or 5K at 60Hz
- FP16/BF16³—
- FP32—
- FP64—
- FP8/FP6 Training³—
- GPU Clock SpeedUp to 1.85 GHz, 1.70 GHz, 1.35 GHz
- GPU Memory | Bandwidth—
- GPU NameQualcomm® Adreno™
- GPU Part NumberX2-90, X2-85
- GPUs in 100 MW¹—
- Inlet Temp—
- Memory BandwidthUp to 135 GB/s
- Memory TypeLPDDR5x
- Networking Bandwidth (Scale-Out)´—
- npu80 TOPS
- NPU NameQualcomm® Hexagon™
- NPU Tera Operations Per SecondUp to 85 TOPS
- Number of CoresUp to 18
- NVFP4 Inference²—
- NVFP4 Training³—
- NVIDIA NVLink—
- NVLink Bandwidth—
- NVLink-C2C Bandwidth—
- Part NumberX2E-80-100, X2E-88-100, X2E-96-100, X2E-94-100, X2E-90-100, X2E-78-100
- Storage Connectionvia M.2 PCIe 3.0.
- Storage InterfaceSD Express, UHS-I
- TF32³—
- Total NVIDIA + HBM4 Chips—
- Video Codec SupportAV1, HEVC, AVC