Can I deploy NVIDIA H200 NVL or NVIDIA GB200 on Runcrate today?

NVIDIA H200 NVL is on demand in 2 regions from $4.63/hr, billed by the second on most GPUs. NVIDIA GB200 is not in stock on Runcrate right now; reserve a cluster, and once we've verified your company and your need we take your exact spec to GPU owners that fit.

How much VRAM does each GPU have?

NVIDIA H200 NVL has 141GB HBM3e. NVIDIA GB200 has 186GB HBM3e.

H200 NVL or GB200: which holds a 70B model in 8-bit weights?

It needs 70 GB of 8-bit weights. On the H200 NVL: 1 GPU, 71 GB spare. On the GB200: 1 GPU, 116 GB spare. Pick the GB200: same GPU count, 67% more memory bandwidth.

GPU comparison

H200 NVL vs GB200.

The GB200 is ahead on memory (186 GB vs 141 GB) and speed (3.0x the FP16 throughput and 67% more memory bandwidth). The H200 NVL makes sense when your model fits in 141 GB and its hourly price is lower.

Launch H200 NVL Reserve a cluster

Rent either on Runcrate

H200 NVLfrom $4.63/hr
$0.033 per GB/hr$0.55 per 100 TFLOPS/hr
Launch H200 NVL H200 NVL pricing
GB200Not in stock right now
Reserve a cluster GB200 pricing

Live hourly price, then per GB of memory and per 100 FP16 TFLOPS.

Which is better for

Which to pick for each job. Memory fit and throughput, from the datasheets.

JobH200 NVLGB200Pick

Hold a 70B model in 8-bit weights
70 GB of 8-bit weights
H200 NVL: 1 GPU, 71 GB spare
GB200: 1 GPU, 116 GB spare
GB200. Same GPU count, 67% more memory bandwidth.
Serve an 8B model in 16-bit weights
16 GB of 16-bit weights
H200 NVL: 1 GPU, 125 GB spare
GB200: 1 GPU, 170 GB spare
GB200. Same GPU count, 67% more memory bandwidth.
Fine-tune a 70B model with QLoRA
About 46 GB with 4-bit weights
H200 NVL: 1 GPU, 95 GB spare
GB200: 1 GPU, 140 GB spare
GB200. Same GPU count, 3.0x the FP16 throughput.
Train on a full node
FP16 tensor throughput per node
H200 NVL: 8x, 6,680 TFLOPS, NVLink in groups of 4
GB200: 8x, 20,000 TFLOPS, NVLink
GB200. 3.0x the FP16 throughput per GPU.
Throughput per watt
FP16 TFLOPS per 100 W of TDP
H200 NVL: 139 TFLOPS per 100 W
GB200: 250 TFLOPS per 100 W
GB200. 80% more FP16 per watt.

Compare another pair

Hopper

NVIDIA H200 NVL

from$4.63/hr

Available now · 2 regions

Memory: 141 GB HBM3e
FP16 tensor: 835 TFLOPS
Bandwidth: 4.8 TB/s

Launch H200 NVL Reserve a cluster

Full pricing details

Blackwell

NVIDIA GB200

Not in stock right now

Memory: 186 GB HBM3e
FP16 tensor: 2500 TFLOPS
Bandwidth: 8.0 TB/s

Reserve a cluster Deploy B200 instead

Full pricing details

At a glance

Spec by spec. The longer bar is the better number.

Memory

NVIDIA H200 NVL141 GB

NVIDIA GB200186 GB

Memory bandwidth

NVIDIA H200 NVL4.8 TB/s

NVIDIA GB2008.0 TB/s

FP16 tensor

NVIDIA H200 NVL835 TFLOPS

NVIDIA GB2002500 TFLOPS

FP32

NVIDIA H200 NVL60 TFLOPS

NVIDIA GB20090 TFLOPS

Full specs

The complete spec sheet.

Spec	NVIDIA H200 NVL	NVIDIA GB200
Architecture	Hopper	Blackwell
Memory	141 GB	186 GB
Memory type	HBM3e	HBM3e
Memory bandwidth	4.8 TB/s	8.0 TB/s
FP32	60 TFLOPS	90 TFLOPS
FP16 tensor	835 TFLOPS	2500 TFLOPS
INT8	1670 TOPS	3600 TOPS
TDP	600 W	1000 W
Form factor	PCIe	Superchip
NVLink	In groups of 4	Yes
GPUs per node	8	8
Hourly price (live)	from $4.63/hr	Not in stock right now

Questions

H200 NVL or GB200. What buyers ask first.

Other comparisons