A longitudinal register of GPU models observed on the public fast network. It records presence and worker count, not ownership, capacity, utilisation, price or performance.
Latest census sample: 24 Aug 2026. Page regenerated 2026-08-26 03:11 UTC from the dated archive.
251 days · 39 GPU models · 3,228 model-day observations · 9 models present now · first observed 17 Dec 2025
A dated register of the GPU models observed on the fast network. Thickness is observed worker count on a shared scale. A band that stops is a model no longer observed; LAST OBSERVED marks its final dated appearance in this window. Persistent absence is consistent with operators withdrawing that class, but the census does not establish why.
15 models plotted. 24 further classes peaked below 5 and are retained in the complete census and the table below.
| Class | First observed | Last observed | Now | Peak | In figure |
|---|---|---|---|---|---|
| RTX 4090 | 2025-12-17 | 2026-08-24 | 48 | 56 | yes |
| RTX 5090 | 2025-12-17 | 2026-08-24 | 29 | 40 | yes |
| RTX PRO 6000 Blackwell Server Edition | 2025-12-17 | 2026-08-24 | 6 | 6 | yes |
| RTX PRO 5000 Blackwell | 2026-05-29 | 2026-08-24 | 6 | 6 | yes |
| RTX PRO 6000 Blackwell Workstation Edition | 2025-12-17 | 2026-08-24 | 2 | 8 | yes |
| RTX 4080 | 2025-12-17 | 2026-08-24 | 2 | 2 | yes |
| RTX 5070 Ti | 2025-12-17 | 2026-08-24 | 1 | 3 | yes |
| RTX PRO 4500 Blackwell | 2026-04-15 | 2026-08-24 | 1 | 2 | yes |
| RTX 3080 | 2026-05-16 | 2026-08-24 | 1 | 1 | yes |
| RTX 3090 | 2025-12-17 | 2026-07-19 | 0 | 42 | yes |
| H100 80GB HBM3 | 2025-12-17 | 2026-07-29 | 0 | 21 | yes |
| B200 | 2025-12-17 | 2026-03-08 | 0 | 12 | yes |
| L40S | 2025-12-17 | 2026-08-18 | 0 | 11 | yes |
| RTX 3090 Ti | 2025-12-17 | 2026-04-17 | 0 | 6 | yes |
| RTX 5080 | 2025-12-17 | 2026-08-03 | 0 | 5 | yes |
| L4 (22GB) | 2026-03-02 | 2026-03-11 | 0 | 4 | no |
| H100 NVL | 2025-12-17 | 2026-05-19 | 0 | 4 | no |
| RTX 6000 Ada Generation | 2025-12-17 | 2026-07-29 | 0 | 4 | no |
| Unknown GPU | 2026-03-12 | 2026-07-05 | 0 | 4 | no |
| RTX 4080 SUPER | 2025-12-17 | 2026-08-23 | 0 | 3 | no |
| RTX 4090 D | 2026-01-06 | 2026-08-22 | 0 | 3 | no |
| A100 80GB PCIe | 2025-12-25 | 2025-12-26 | 0 | 2 | no |
| RTX 5060 Ti | 2025-12-31 | 2026-07-28 | 0 | 2 | no |
| RTX PRO 6000 Blackwell Max-Q Workstation Edition | 2026-03-28 | 2026-03-28 | 0 | 2 | no |
| B300 SXM6 AC | 2025-12-17 | 2025-12-17 | 0 | 2 | no |
| L40 | 2025-12-25 | 2025-12-25 | 0 | 1 | no |
| L4 | 2026-02-24 | 2026-03-10 | 0 | 1 | no |
| H200 | 2026-01-07 | 2026-03-30 | 0 | 1 | no |
| H100 PCIe | 2026-01-02 | 2026-07-17 | 0 | 1 | no |
| RTX 5090 D | 2026-03-23 | 2026-08-16 | 0 | 1 | no |
| Graphics Device | 2026-07-26 | 2026-07-27 | 0 | 1 | no |
| RTX A4500 | 2026-04-26 | 2026-04-26 | 0 | 1 | no |
| RTX 4070 Ti SUPER | 2026-04-13 | 2026-07-30 | 0 | 1 | no |
| RTX A5000 | 2025-12-17 | 2025-12-20 | 0 | 1 | no |
| RTX A6000 | 2025-12-17 | 2025-12-29 | 0 | 1 | no |
| A800 80GB PCIe | 2025-12-25 | 2026-01-23 | 0 | 1 | no |
| A100-SXM4-40GB | 2026-06-03 | 2026-07-19 | 0 | 1 | no |
| RTX A4000 | 2026-03-06 | 2026-07-22 | 0 | 1 | no |
| RTX 4090 (24GB) | 2026-03-05 | 2026-03-11 | 0 | 1 | no |
Observed workers are concentrated: the leading GPU model holds 48 of 96 observed workers (50%). 6 established classes no longer reach the present.
The census is a separate open dataset. It is not a performance ranking and never weights the goodput ratios.
Scope. One public, unauthenticated fast-network census, sampled once per dated day from 2025-12-17 through 2026-08-24. Counts show observed workers, not capacity, utilisation, price, ownership or the reason a model appeared or disappeared.
Method. Lifelines include every GPU model present now or peaking at 5 workers or more. Band thickness uses one shared scale. The complete table and downloads retain every observed model, including those below the figure threshold.
Separate measurement. Workload-specific production goodput lives at /market. The census is context only and is not combined with it.
Citation. Reuse is licensed under CC BY 4.0.