What's the price difference between NVIDIA H200 NVL and NVIDIA V100?

On Runcrate today, NVIDIA H200 NVL starts at $4.63/hr and NVIDIA V100 starts at $0.36/hr; NVIDIA V100 is cheaper by 92%.

Can I deploy NVIDIA H200 NVL or NVIDIA V100 on Runcrate today?

NVIDIA H200 NVL is on demand in 2 regions from $4.63/hr, billed by the second on most GPUs. NVIDIA V100 is on demand in 2 regions from $0.36/hr, billed by the second on most GPUs.

How much VRAM does each GPU have?

NVIDIA H200 NVL has 141GB HBM3e. NVIDIA V100 has 32GB HBM2.

H200 NVL or V100: 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 V100: 3 GPUs (96 GB). Pick the H200 NVL: fits on one GPU.

GPU comparison

H200 NVL vs V100.

The H200 NVL is ahead on memory (141 GB vs 32 GB) and speed (6.7x the FP16 throughput and 5.3x the memory bandwidth). The V100 makes sense when your model fits in 32 GB and its hourly price is lower.

Launch V100 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
V100Cheaperfrom $0.36/hr
$0.011 per GB/hr$0.29 per 100 TFLOPS/hr
Launch V100 V100 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 NVLV100Pick

Hold a 70B model in 8-bit weights
70 GB of 8-bit weights
H200 NVL: 1 GPU, 71 GB spare
V100: 3 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
V100: 1 GPU, 16 GB spare
H200 NVL. Same GPU count, 5.3x the memory bandwidth.
Fine-tune a 70B model with QLoRA
About 46 GB with 4-bit weights
H200 NVL: 1 GPU, 95 GB spare
V100: 2 GPUs (64 GB)
H200 NVL. Fits on one GPU.
Train on a full node
FP16 tensor throughput per node
H200 NVL: 8x, 6,680 TFLOPS, NVLink in groups of 4
V100: 8x, 1,000 TFLOPS, NVLink
H200 NVL. 6.7x the FP16 throughput per GPU.
Throughput per watt
FP16 TFLOPS per 100 W of TDP
H200 NVL: 139 TFLOPS per 100 W
V100: 42 TFLOPS per 100 W
H200 NVL. 3.3x 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

Volta

NVIDIA V100

from$0.36/hrCheaper

Available now · 2 regions

Memory: 32 GB HBM2
FP16 tensor: 125 TFLOPS
Bandwidth: 900 GB/s

Launch V100 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 V10032 GB

Memory bandwidth

NVIDIA H200 NVL4.8 TB/s

NVIDIA V100900 GB/s

FP16 tensor

NVIDIA H200 NVL835 TFLOPS

NVIDIA V100125 TFLOPS

Hourly price, from (live)

NVIDIA H200 NVL$4.63/hr

NVIDIA V100$0.36/hr

Full specs

The complete spec sheet.

Spec	NVIDIA H200 NVL	NVIDIA V100
Architecture	Hopper	Volta
Memory	141 GB	32 GB
Memory type	HBM3e	HBM2
Memory bandwidth	4.8 TB/s	900 GB/s
FP32	60 TFLOPS	15.7 TFLOPS
FP16 tensor	835 TFLOPS	125 TFLOPS
INT8	1670 TOPS	125 TOPS
TDP	600 W	300 W
Form factor	PCIe	PCIe
NVLink	In groups of 4	Yes
GPUs per node	8	8
Hourly price (live)	from $4.63/hr	from $0.36/hr

Questions

H200 NVL or V100. What buyers ask first.

Other comparisons