runaiicloud
ModelsAppsGPUsServerless GPUPricingReserveDocsConnectCompareEnterprise
Log inGet started
Home/GPUs/8× NVIDIA RTX PRO 6000 Blackwell 96GB
DIEHBMINTERPOSERNVSWITCHSUBSTRATESUBSTRATE · POWER & THERMALINTERPOSER · NVLink-C2C FABRICHBMHBMHBMHBMRTXFP8 · 8×NVSWITCH

Workstation ×8 · FP8

8× NVIDIA RTX PRO 6000 Blackwell 96GB

$19.2/hr $0.0053/sec · $14,016/mo at 24/7

g4-standard-384 — full-node Blackwell.

VRAM pool

8× NVIDIA RTX PRO 6000 Blackwell 96GB

Deploy this →Configure sizeCompare providers →

What you're renting

Compute die

NVIDIA RTX PRO 6000 Blackwell 96GB — FP8 tensor cores.

GDDR7 memory

768 GB of GDDR7 across the 8 GPUs.

PCIe Gen5 interconnect

PCIe Gen5 host links — 8 GPUs, each on its own link.

Per-second metering

$19.2/hr → 0.0053/sec. Pause the deployment and the meter hits $0.

Scale-to-zero

Autoscale + region pins (GLOBAL / US / EU / APAC) on the control plane.

Reserve it in minutesDeploy →

What fits here

Memory budget

768 GB of VRAM on this preset. 70B+ dense checkpoints fit with room for KV cache (rule of thumb: about one byte per parameter at FP8).

Typical loads

multi-tenant inference, parallel eval harnesses, 70B+ dense serving. Fine on: torch, JAX, raw CUDA, axolotl, vLLM, sglang, ComfyUI.

Billing math

$19.2/hr is $0.0053/sec while running and $0 while parked; park/wake freezes and restores state instead of paying for idle.

Sizing this preset

Best fit

768 GB across eight RTX PRO 6000 Blackwell cards at $19.20/hr, $2.40 per GPU-hour — the catalog's full-node RTX PRO 6000 row. Eight separate 96 GB GDDR7 budgets on PCIe Gen5, or one ~700B FP8 checkpoint split eight ways with ~68 GB left for KV cache (rule of thumb).

Trade-off

The next rung is b200-4x-fp4 at $40/hr — about double — and it is a different architecture, not more of the same: four B200 180 GB cards, 720 GB of HBM3e on NVLink 5 at NVFP4. That is slightly less total VRAM than 768 GB but a shared GPU fabric and the catalog's 4-bit mode; for independent workers, g4-8x gives eight cards and more VRAM for half the hourly.

Questions about this preset

What does the Workstation ×8 preset (8× NVIDIA RTX PRO 6000 Blackwell 96GB) cost per hour?

$19.2/hr on runaii.cloud, metered per second: $0.0053/sec while the VM runs and $0 while parked. A month of 24/7 uptime would be about $14,016, and park/wake means busy-fraction pricing in practice.

Is the Workstation ×8 (8× NVIDIA RTX PRO 6000 Blackwell 96GB) billed by the second?

Yes. Per-second metering with park/wake: idle freezes the VM state into a signed artifact and stops the meter the same second; the next request wakes it byte-exact

What fits on the Workstation ×8 (8 GPUs pooled)?

768 GB of VRAM. 70B+ dense checkpoints fit with room for KV cache (rule of thumb: about one byte per parameter at FP8).

How much VRAM does g4-8x have?

768 GB — eight 96 GB GDDR7 cards at $19.20/hr, $2.40 per GPU-hour.

Why move from g4-8x to b200-4x-fp4?

For HBM3e and NVLink 5: b200-4x-fp4 is four 180 GB B200 cards on a shared fabric at $40/hr, against eight independent 96 GB GDDR7 cards at $19.20/hr.

What fits in 768 GB?

A ~700B FP8 checkpoint split eight ways with ~68 GB left for KV cache, or eight independent 70B checkpoints — one per card (rule of thumb).

Sizing ladder

RTX PRO 6000 slices

from $0.30/hr · 12-48GB

Blackwell slices for light jobs

1× NVIDIA T4 16GB

$0.44/hr · FP16

Starter

1× NVIDIA L4 24GB

$0.87/hr · FP8

Efficient

2× NVIDIA L4 24GB

$1.8/hr · FP8

Efficient ×2

4× NVIDIA L4 24GB

$3.6/hr · FP8

Efficient ×4

8× NVIDIA L4 24GB

$7.2/hr · FP8

Efficient ×8

1× NVIDIA RTX PRO 6000 Blackwell 96GB

$2.4/hr · FP8

Workstation

2× NVIDIA RTX PRO 6000 Blackwell 96GB

$4.8/hr · FP8

Workstation ×2

4× NVIDIA RTX PRO 6000 Blackwell 96GB

$9.6/hr · FP8

Workstation ×4

8× NVIDIA B300 288GB

$96/hr · FP8

Full Precision

8× NVIDIA B200 180GB

$80/hr · NVFP4

Throughput

4× NVIDIA B300 288GB

$48/hr · NVFP4

Minimal

4× NVIDIA B200 180GB

$40/hr · NVFP4

Efficient

16× NVIDIA GB300

$184/hr · FP8

Frontier Max

See all presets on /gpus →

runaiicloud

Serverless inference, dedicated GPUs, and training for open models. OpenAI- and Anthropic-compatible APIs.

© 2026 runaii

Platform

Model libraryAppsGPUsServerless GPUPricingToken-Max coding plansCompare providersDocs

Developers

ConnectCookbookCLIAgents / MCPUse casesTutorialsBlogFAQ

Company

EnterpriseStartupsAboutCareersTrust centerStatusSupportTermsPrivacyData policySubprocessorsSitemap