What's the price difference between NVIDIA H200 NVL and NVIDIA A40?

On Runcrate today, NVIDIA H200 NVL starts at $4.63/hr and NVIDIA A40 starts at $2.42/hr; NVIDIA A40 is cheaper by 48%.

Can I deploy NVIDIA H200 NVL or NVIDIA A40 on Runcrate today?

NVIDIA H200 NVL is on demand in 2 regions from $4.63/hr, billed by the second on most GPUs. NVIDIA A40 is on demand in 1 region from $2.42/hr, billed by the second on most GPUs.

How much VRAM does each GPU have?

NVIDIA H200 NVL has 141GB HBM3e. NVIDIA A40 has 48GB GDDR6.

H200 NVL or A40: 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 A40: 2 GPUs (96 GB). Pick the H200 NVL: fits on one GPU.

GPU comparison

H200 NVL vs A40.

The H200 NVL is ahead on memory (141 GB vs 48 GB) and speed (5.6x the FP16 throughput and 6.9x the memory bandwidth). The A40 makes sense when your model fits in 48 GB and its hourly price is lower.

Launch A40 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
A40Cheaperfrom $2.42/hr
$0.050 per GB/hr$1.62 per 100 TFLOPS/hr
Launch A40 A40 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 NVLA40Pick

Hold a 70B model in 8-bit weights
70 GB of 8-bit weights
H200 NVL: 1 GPU, 71 GB spare
A40: 2 GPUs (96 GB)
H200 NVL. Fits on one GPU.
Serve an 8B model in 16-bit weights
16 GB of 16-bit weights
H200 NVL: 1 GPU, 125 GB spare
A40: 1 GPU, 32 GB spare
H200 NVL. Same GPU count, 6.9x the memory bandwidth.
Fine-tune a 70B model with QLoRA
About 46 GB with 4-bit weights
H200 NVL: 1 GPU, 95 GB spare
A40: 1 GPU, 2 GB spare
H200 NVL. Same GPU count, 5.6x the FP16 throughput.
Train on a full node
FP16 tensor throughput per node
H200 NVL: 8x, 6,680 TFLOPS, NVLink in groups of 4
A40: 4x, 599 TFLOPS
H200 NVL. 8 GPUs per node, not 4.
Throughput per watt
FP16 TFLOPS per 100 W of TDP
H200 NVL: 139 TFLOPS per 100 W
A40: 50 TFLOPS per 100 W
H200 NVL. 2.8x the 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

Ampere

NVIDIA A40

from$2.42/hrCheaper

Available now · 1 region

Memory: 48 GB GDDR6
FP16 tensor: 149.7 TFLOPS
Bandwidth: 696 GB/s

Launch A40 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 A4048 GB

Memory bandwidth

NVIDIA H200 NVL4.8 TB/s

NVIDIA A40696 GB/s

FP16 tensor

NVIDIA H200 NVL835 TFLOPS

NVIDIA A40149.7 TFLOPS

Hourly price, from (live)

NVIDIA H200 NVL$4.63/hr

NVIDIA A40$2.42/hr

Full specs

The complete spec sheet.

Spec	NVIDIA H200 NVL	NVIDIA A40
Architecture	Hopper	Ampere
Memory	141 GB	48 GB
Memory type	HBM3e	GDDR6
Memory bandwidth	4.8 TB/s	696 GB/s
FP32	60 TFLOPS	37.4 TFLOPS
FP16 tensor	835 TFLOPS	149.7 TFLOPS
INT8	1670 TOPS	299 TOPS
TDP	600 W	300 W
Form factor	PCIe	PCIe
NVLink	In groups of 4	No
GPUs per node	8	4
Hourly price (live)	from $4.63/hr	from $2.42/hr

Questions

H200 NVL or A40. What buyers ask first.

Other comparisons