B200 vs A16
Explore a head to head comparison of specifications, performance, and pricing.
B200
The NVIDIA B200 delivers high-performance computing capabilities for AI, machine learning, and data science applications.
ManufacturerNVIDIA
GPU Architecture—
Average Price$20.84/hr
GPU VRAM192 GB
Cloud Availability4 clouds
System Memory2900 GB
CPU Cores248
Storage30.7 TB
A16
The NVIDIA A16 delivers high-performance computing capabilities for AI, machine learning, and data science applications.
ManufacturerNVIDIA
GPU Architecture—
Average Price$3.37/hr
GPU VRAM64 GB
Cloud Availability1 clouds
System Memory960 GB
CPU Cores96
Storage1.7 TB
See how the B200 & A16 compare
Compare detailed hardware specifications and average pricing for the B200 and A16.
Compare Hardware Specifications
| B200 | A16 | |
|---|---|---|
| GPU Type | B200 | A16 |
| VRAM per GPU | 192 GB | 64 GB |
| Manufacturer | NVIDIA | NVIDIA |
| Architecture | Blackwell | Ampere |
| Interconnect | SXM6 | PCIe Gen4 |
| Memory Bandwidth | 8 TB/s | 4x 200 GB/s |
| FP16 TFLOPS | 1,191.2 TFLOPS (16:1) | 4.493 TFLOPS (1:1) |
| CUDA Cores | 20480 | 4x 1,280 |
| Tensor Cores | 640 (5th Gen) | 4x 40 (3rd Gen) |
| RT Cores | N/A | 4x 10 (2nd Gen) |
| Base Clock | 700 MHz | 1312 MHz |
| Boost Clock | 1965 MHz | 1755 MHz |
| TDP | 1000W | 250W |
| Process Node | TSMC 4NP | TSMC 8nm |
| Data Formats | FP4, FP6, FP8, INT8, BF16, FP16, TF32, FP32, FP64 | INT8, BF16, FP16, TF32, FP32 |
Compare Average On-Demand Pricing
| B200 | A16 | |
|---|---|---|
| 1 GPU | $5.46 /hr | $0.51 /hr |
| 2 GPUs | $10.00 /hr | $1.02 /hr |
| 4 GPUs | $18.98 /hr | $2.05 /hr |
| 8 GPUs | $34.88 /hr | $4.09 /hr |
Explore B200 & A16 Instances
Browse available instances with B200 and A16 GPUs. Filter by provider, availability, and more to find the perfect instance for your needs.
Explore more GPU comparisons
Select any two GPUs to compare their specifications and explore pricing across providers.
