Which holds more GPU memory?

CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory), at 768 GB across the instance against 96 GB. Per board it is 96 GB against 96 GB.

What would a week cost?

$3,360 for CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory) and $284 for RunPod RTX Pro 6000 · Community Cloud, at 168 hours of the whole machine at its published rate, with no commitment discount. Where a spot rate is published the same week costs less and the machine can be taken back mid-run.

What does the hourly price leave out?

CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory): disk 7.7 TB, 2 regions listed, billed per hour. RunPod RTX Pro 6000 · Community Cloud: disk none, billed separately, no regions published, billed per second. Egress and tax are extra on both.

CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory) vs RunPod RTX Pro 6000 · Community Cloud.

machine vs machine · prices as of 17 Sept 2026

The same RTX PRO 6000 at two providers, so the board is identical and everything else is not. RunPod RTX Pro 6000 · Community Cloud takes 2 of 4 rounds against CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory). It is also the cheaper of the two by the hour, at $1.69/GPU-hr against $2.50/GPU-hr.

CoreWeave

NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory)

$2.50/GPU-hr

$20/hr for the machine · $3,360 a week · $1.38 spot

8x RTX PRO 6000 · 96 GB each · $0.0260/GB-hr

CoreWeave ↗

RunPodwins 2 rounds

RTX Pro 6000 · Community Cloud

$1.69/GPU-hr

$1.69/hr for the machine · $284 a week

1x RTX PRO 6000 · 96 GB each · $0.0176/GB-hr · Marketplace

RunPod ↗

Price per GPU-hour (lower wins)

$2.50/GPU-hr

$1.69/GPU-hr

Interruptible rate (lower wins)

$1.38/GPU-hr

not published

Price per GB of VRAM (lower wins)

$0.0260/GB-hr

$0.0176/GB-hr

VRAM per GPU

96 GB

GPUs per instance

8x RTX PRO 6000

1x RTX PRO 6000

vCPU

128

RAM

1024 GB

188 GB

Included storage

7.7 TB

none · volumes extra

Regions listed

2 regions

regions not stated

What a run costs on each

An hour of the machine$20/hr vs $1.69/hr
A day$480 vs $41
A week$3,360 vs $284
A week on spot$1,849 vs not published

CoreWeave then RunPod, at the published rate with no commitment discount

Go further

open in the compare tool →every price for the RTX PRO 6000

Add a third or fourth machine, or switch the weighting, in the tool.

Frequently asked

Which is cheaper, CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory) or RunPod RTX Pro 6000 · Community Cloud?: RunPod RTX Pro 6000 · Community Cloud, at $1.69/GPU-hr against $2.50/GPU-hr, both the on-demand rate for one GPU for one hour, read on 17 Sept 2026. On the whole machine that is $1.69/hr against $20/hr.
Which holds more GPU memory?: CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory), at 768 GB across the instance against 96 GB. Per board it is 96 GB against 96 GB.
What would a week cost?: $3,360 for CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory) and $284 for RunPod RTX Pro 6000 · Community Cloud, at 168 hours of the whole machine at its published rate, with no commitment discount. Where a spot rate is published the same week costs less and the machine can be taken back mid-run.
What does the hourly price leave out?: CoreWeave NVIDIA RTX PRO 6000 Blackwell Server Edition (High Memory): disk 7.7 TB, 2 regions listed, billed per hour. RunPod RTX Pro 6000 · Community Cloud: disk none, billed separately, no regions published, billed per second. Egress and tax are extra on both.

Every rate is the on-demand price for one GPU for one hour, read 17 Sept 2026 from each provider's own page, so a node of eight is compared at what one of its GPUs costs. Storage, egress and tax are extra unless a row says otherwise, and reserved or committed rates are not indexed. Bars are scaled to the larger value in each row.