The Vera Rubin is newer, with 14x the memory and 69x the bandwidth.
At a glance
Memory
14x more on Vera Rubin
- RTX 4000 SFF Ada
- 20 GB
- Vera Rubin
- 288 GB
Memory bandwidth
69x higher on Vera Rubin
- RTX 4000 SFF Ada
- 280 GB/s
- Vera Rubin
- 19,200 GB/s
Cheapest on-demand
Vera Rubin is not sold on demand
- RTX 4000 SFF Ada
- $0.50 /GPU/hr
- Vera Rubin
- --
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | RTX 4000 SFF Ada | Vera Rubin | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.50 | No on-demand listings | |
| Reserved | No reserved listings | -- /GPU/hr |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for on-demand on the RTX 4000 SFF Ada and reserved on the Vera Rubin: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
RTX 4000 SFF Ada vs Vera Rubin price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | RTX 4000 SFF Ada | Vera Rubin | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 20 GB GDDR6 | 288 GB HBM4 | 14x more on Vera Rubin |
| Bandwidth | 280 GB/s | 19,200 GB/s | 69x higher on Vera Rubin |
| Bus width | 160-bit | ||
| Compute · dense | |||
| FP4 | Not supported | 35,000 TFLOPS | Vera Rubin only |
| FP8 | 153.4 TFLOPS | 17,500 TFLOPS | 114x higher on Vera Rubin |
| FP16 / BF16 | 76.7 TFLOPS | 4,000 TFLOPS | 52x higher on Vera Rubin |
| INT8 | 250 TOPS | ||
| FP32 | 19.2 TFLOPS | 130 TFLOPS | 6.8x higher on Vera Rubin |
| FP64 | Not supported | 33 TFLOPS | Vera Rubin only |
| Platform | |||
| Interconnect | PCIe only | NVLink 3,000 GB/s | NVLink on Vera Rubin only |
| Released | Q2 2023 | Q1 2026 | 3 years newer on Vera Rubin |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32INT4INT8 | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 4000 SFF Ada datasheet and Vera Rubin datasheet.
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | RTX 4000 SFF Ada | Vera Rubin |
|---|---|---|
|
|
$0.50 /GPU/hr On-demand | -- |
|
|
$0.18 /GPU/hr On-demand | -- |
|
|
-- | $11.05 /GPU/hr Reserved NVL |
|
|
-- | On request Custom |
|
|
-- | On request Custom NVL |
|
|
-- | On request Custom NVL |
|
|
-- | On request Custom NVL |
|
|
-- | On request Custom NVL |
Similar GPUs
Other comparisons in the same class.
-
-
Nvidia RTX 4000 Ada
20 GB GDDR6 · 29% more bandwidth than the RTX 4000 SFF Ada
On-demand from $0.52 /GPU/hr -
Nvidia A4000
16 GB GDDR6 · 60% more bandwidth than the RTX 4000 SFF Ada
On-demand from $0.10 /GPU/hr -
Nvidia B300
288 GB HBM3e · 58% less bandwidth than the Vera Rubin
On-demand from $5.57 /GPU/hr -
Nvidia GB300
288 GB HBM3e · 58% less bandwidth than the Vera Rubin
On-demand from $18.00 /GPU/hr
Our data for Nvidia RTX 4000 SFF Ada was last updated on Sept. 14, 2026, and for Nvidia Vera Rubin on Nov. 9, 2026.