Compare GPUs
Specifications with their sources, measured runs where the conditions match, current offering prices and the memory fit of your workload. Accelerators are never ranked by peak FLOPS.
Specifications
vendor datasheet (RA-BIT v2 spec registry) and Kovara registry, per fieldSupported precisions
dense tensor peak| Dense peak | NVIDIA H100 SXM | NVIDIA H200 SXM | NVIDIA B200 SXM 180GB |
|---|---|---|---|
| FP32 | 67TFLOPS | 67TFLOPS | — |
| TF32 | 494.5TFLOPS | 494.5TFLOPS | 1,125 |
Current Kovara offerings
active, public, not archived| Accelerator | Comparable price range | Live offerings | Providers | Latest check | |
|---|---|---|---|---|---|
| NVIDIA H100 SXM | $0.79–$12.29USD / GPU-hour | 79 | 29 | 2026-11-17 | Offerings → |
| NVIDIA H200 SXM | $0.79–$10.60USD / GPU-hour |
Measured evidence
MeasuredRun a benchmarkNo published runs share the same conditions across these accelerators yet. Per accelerator: NVIDIA H100 SXM: 0 runs · NVIDIA H200 SXM: 0 runs · NVIDIA B200 SXM 180GB: 0 runs.
Your workload
memory fit and decode rangeName a published model (or a parameter count), the weight precision, the context and how many sequences must run at once. RA-BIT v2 then sizes memory and an analytical decode range for each accelerator.
Share this view: permalink