Minimal · NVFP4

4× NVIDIA B300 288GB

$48/hr $0.0133/sec · $35,040/mo at 24/7

Smallest frontier-capable footprint. Smallest frontier-capable footprint.

VRAM pool

288GB ×4 = 1.1TB

Position

vs H200 4×: lower $/hr, more VRAM

Deploy this →Configure size Compare providers →

What you're renting

Compute die

NVIDIA B300 288GB — NVFP4 tensor cores, tuned for smallest frontier-capable footprint.

HBM stack

288GB ×4 = 1.1TB of high-bandwidth attached memory — the whole model fits, no offload.

Interposer / NVLink

NVLink-C2C fabric so the 4 GPUs act like one pool.

Per-second metering

$48/hr → 0.0133/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 →

Other presets

8× NVIDIA B300 288GB

$96/hr · FP8

Max quality for frontier dense models

8× NVIDIA B200 180GB

$80/hr · NVFP4

Best tokens/$ for large MoE models

4× NVIDIA B200 180GB

$40/hr · NVFP4

Great for ≤70B dense models

16× NVIDIA GB300

$184/hr · FP8

For 1T+ parameter models

runaiicloud

← All GPUs