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 GeForce RTX 3060 Reference specificationGPU0096 |
|---|---|
| Memory capacity | 12GBKovara registry · verified 2026-09-23 |
| Memory type | GDDR6Kovara registry · verified 2026-09-23 |
| Memory bandwidth | —Not published |
| Board power (TDP) | 170WKovara registry · verified 2026-09-23 |
| Form factor | PCIe consumerKovara registry · verified 2026-09-23 |
| NVLink | —Not published |
| MIG partitioning | —Not published |
Supported precisions
dense tensor peak| Dense peak | NVIDIA GeForce RTX 3060 Reference specification |
|---|---|
| FP32 | — |
| TF32 | — |
| BF16 | — |
| FP16 | — |
| FP8 | — |
| FP4 |
Current Kovara offerings
active, public, not archived| Accelerator | Comparable price range | Live offerings | Providers | Latest check | |
|---|---|---|---|---|---|
| NVIDIA GeForce RTX …cation | — | 1 | 1 | 2026-11-01 | Offerings → |
Measured evidence
MeasuredRun a benchmarkNo published runs share the same conditions across these accelerators yet. Per accelerator: NVIDIA GeForce RTX 3060 Reference specification: 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