What's the price difference between NVIDIA H200 NVL and NVIDIA A100 80GB?

On Runcrate today, NVIDIA H200 NVL starts at $4.63/hr and NVIDIA A100 80GB starts at $1.73/hr; NVIDIA A100 80GB is cheaper by 63%.

Can I deploy NVIDIA H200 NVL or NVIDIA A100 80GB on Runcrate today?

NVIDIA H200 NVL is on demand in 2 regions from $4.63/hr, billed by the second on most GPUs. NVIDIA A100 80GB is on demand in 6 regions from $1.73/hr, billed by the second on most GPUs.

How much VRAM does each GPU have?

NVIDIA H200 NVL has 141GB HBM3e. NVIDIA A100 80GB has 80GB HBM2e.

H200 NVL or A100 80GB: 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 A100 80GB: 1 GPU, 10 GB spare. Pick the H200 NVL: same GPU count, at least 2.3x the memory bandwidth.

GPU comparison

H200 NVL vs A100 80GB.

The H200 NVL is ahead on memory (141 GB vs 80 GB) and speed (2.7x the FP16 throughput and at least 2.3x the memory bandwidth). The A100 80GB makes sense when your model fits in 80 GB and its hourly price is lower.

Launch A100 80GB 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
A100 80GBCheaperfrom $1.73/hr
$0.022 per GB/hr$0.55 per 100 TFLOPS/hr
Launch A100 80GB A100 80GB 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 NVLA100 80GBPick

Hold a 70B model in 8-bit weights
70 GB of 8-bit weights
H200 NVL: 1 GPU, 71 GB spare
A100 80GB: 1 GPU, 10 GB spare
H200 NVL. Same GPU count, at least 2.3x the memory bandwidth.
Serve an 8B model in 16-bit weights
16 GB of 16-bit weights
H200 NVL: 1 GPU, 125 GB spare
A100 80GB: 1 GPU, 64 GB spare
H200 NVL. Same GPU count, at least 2.3x the memory bandwidth.
Fine-tune a 70B model with QLoRA
About 46 GB with 4-bit weights
H200 NVL: 1 GPU, 95 GB spare
A100 80GB: 1 GPU, 34 GB spare
H200 NVL. Same GPU count, 2.7x the FP16 throughput.
Train on a full node
FP16 tensor throughput per node
H200 NVL: 8x, 6,680 TFLOPS, NVLink in groups of 4
A100 80GB: 8x, 2,496 TFLOPS
H200 NVL. 2.7x the FP16 throughput per GPU.
Throughput per watt
FP16 TFLOPS per 100 W of TDP
H200 NVL: 139 TFLOPS per 100 W
A100 80GB: Varies by card
Either. Varies by card.

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

Ampere

NVIDIA A100 80GB

from$1.73/hrCheaper

Available now · 6 regions

Memory: 80 GB HBM2e
FP16 tensor: 312 TFLOPS
Bandwidth: up to 2.0 TB/s

Launch A100 80GB Reserve a cluster

Full pricing details

At a glance

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

Memory

NVIDIA H200 NVL141 GB

NVIDIA A100 80GB80 GB

Memory bandwidth

NVIDIA H200 NVL4.8 TB/s

NVIDIA A100 80GBup to 2.0 TB/s

FP16 tensor

NVIDIA H200 NVL835 TFLOPS

NVIDIA A100 80GB312 TFLOPS

Hourly price, from (live)

NVIDIA H200 NVL$4.63/hr

NVIDIA A100 80GB$1.73/hr

Full specs

The complete spec sheet.

Spec	NVIDIA H200 NVL	NVIDIA A100 80GB
Architecture	Hopper	Ampere
Memory	141 GB	80 GB
Memory type	HBM3e	HBM2e
Memory bandwidth	4.8 TB/s	up to 2.0 TB/s
FP32	60 TFLOPS	19.5 TFLOPS
FP16 tensor	835 TFLOPS	312 TFLOPS
INT8	1670 TOPS	624 TOPS
TDP	600 W	up to 400 W
GPUs per node	8	8
Hourly price (live)	from $4.63/hr	from $1.73/hr

Questions

H200 NVL or A100 80GB. What buyers ask first.

Other comparisons