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 field| Specification | NVIDIA H200 141GB — provider does not specify SXM/NVLGPU0092 |
|---|---|
| Memory capacity | 141GBKovara registry · verified 2026-09-25 |
| Memory type | HBM3EKovara registry · verified 2026-09-25 |
| Memory bandwidth | 4.8TB/sKovara registry · verified 2026-09-25 |
| Board power (TDP) | —Not published |
| Form factor | —Not published |
| NVLink | YesKovara registry · verified 2026-09-25 |
| MIG partitioning | YesKovara registry · verified 2026-09-25 |
Supported precisions
dense tensor peak| Dense peak | NVIDIA H200 141GB — provider does not specify SXM/NVL |
|---|---|
| FP32 | — |
| TF32 | — |
| BF16 | — |
| FP16 | — |
| FP8 | — |
| FP4 |
Current Kovara offerings
active, public, not archived| Accelerator | Comparable price range | Live offerings | Providers | Latest check | |
|---|---|---|---|---|---|
| NVIDIA H200 141GB —…XM/NVL | $5.29–$6.99USD / GPU-hour | 14 | 7 | 2026-11-17 | Offerings → |
Measured evidence
MeasuredRun a benchmarkNo published runs share the same conditions across these accelerators yet. Per accelerator: NVIDIA H200 141GB — provider does not specify SXM/NVL: 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