NVIDIA B200 SXM 180GB vs NVIDIA GB10 Grace Blackwell

The GB10 Grace Blackwell is the newer part: Blackwell, launched in 2025, against the B200's Blackwell from 2024. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the B200 against the GB10 Grace Blackwell: FP32 75 vs 31 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 180 GB against 128 GB, fed at 7.7 TB/s versus 273 GB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

Power budgets are 1.0 kW for the B200 and 180 W for the GB10 Grace Blackwell. At FP32 that works out to 0.07 against 0.17 TFLOPS per watt.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.