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 RTX PRO 6000 Blackwell Max-Q Workstation EditionGPU0119 |
|---|---|
| Memory capacity | 96GBKovara registry · verified 2026-10-02 |
| Memory type | GDDR7Kovara registry · verified 2026-10-02 |
| Memory bandwidth | 1.79TB/sKovara registry · verified 2026-10-02 |
| Board power (TDP) | 300WKovara registry · verified 2026-10-02 |
| Form factor | PCIe Gen5 dual-slotKovara registry · verified 2026-10-02 |
| NVLink | —Not published |
| MIG partitioning | YesKovara registry · verified 2026-10-02 |
Supported precisions
dense tensor peak| Dense peak | NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition |
|---|---|
| FP32 | — |
| TF32 | — |
| BF16 | — |
| FP16 | — |
| FP8 | — |
| FP4 |
Current Kovara offerings
active, public, not archived| Accelerator | Comparable price range | Live offerings | Providers | Latest check | |
|---|---|---|---|---|---|
| NVIDIA RTX PRO 6000…dition | — | 6 | 1 | 2026-10-02 | Offerings → |
Measured evidence
MeasuredRun a benchmarkNo published runs share the same conditions across these accelerators yet. Per accelerator: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition: 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