NVIDIA H100 PCIe 80GB vs NVIDIA H100 NVL 94GB

The H100 NVL 94GB delivers 18% more FP32 throughput than the H100 PCIe 80GB (60 vs 51 TFLOPS dense). The H100 NVL 94GB also carries 14 GB more memory (94 GB vs 80 GB).

H100 PCIe 80GB: Hopper, 2022 H100 NVL 94GB: Hopper, 2023
FP32 dense lead
+18%
H100 NVL 94GB: 60 vs 51 TFLOPS
VRAM
80 vs 94 GB
14 GB more for the H100 NVL 94GB
Bandwidth
2.0 TB/s vs 3.9 TB/s
H100 NVL 94GB moves data faster
TDP
350 W vs 400 W
H100 PCIe 80GB draws 50 W less

Specifications

H100 PCIe 80GB
H100 NVL 94GB
Architecture
HopperHopper
Launch Year
20222023
Form Factor
PCIePCIe
VRAM
80 GB94 GB
Memory Bandwidth
2.0 TB/s3.9 TB/s
TDP
350 W400 W
Process Node
4nm4nm

Performance (TFLOPS)

H100 PCIe 80GB
H100 NVL 94GB
FP64
26.0 TFlops 30.0 TFlops
FP32
51.0 TFlops 60.0 TFlops
FP16
756.5 TFlops
sparse not published
BF16
756.5 TFlops
sparse not published
FP8
1513.0 TFlops
sparse not published
INT8
1513.0 TFlops
sparse not published
Tensor Core
FP64 (TC)
60.0 TFlops

FLOPS by Precision

What actually differs

The H100 NVL 94GB is the newer part: Hopper, launched in 2023, against the H100 PCIe 80GB's Hopper from 2022. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the H100 PCIe 80GB against the H100 NVL 94GB: FP64 26 vs 30 TFLOPS, FP32 51 vs 60 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 80 GB against 94 GB, fed at 2.0 TB/s versus 3.9 TB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

Power budgets are 350 W for the H100 PCIe 80GB and 400 W for the H100 NVL 94GB. At FP32 that works out to 0.15 against 0.15 TFLOPS per watt.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.

Frequently asked questions

Is the H100 PCIe 80GB faster than the H100 NVL 94GB?

At FP32 precision the H100 NVL 94GB reaches 60 TFLOPS dense against 51 TFLOPS for the H100 PCIe 80GB. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the H100 PCIe 80GB or the H100 NVL 94GB?

The H100 NVL 94GB carries 94 GB of VRAM versus 80 GB for the H100 PCIe 80GB. Memory bandwidth is 2.0 TB/s for the H100 PCIe 80GB and 3.9 TB/s for the H100 NVL 94GB.

How much power do the H100 PCIe 80GB and the H100 NVL 94GB draw?

The H100 PCIe 80GB is rated at 350 W TDP and the H100 NVL 94GB at 400 W. On FP32 throughput per watt, the H100 NVL 94GB is the more efficient part.

Can I rent the H100 PCIe 80GB or the H100 NVL 94GB in the cloud?

Yes. Live cloud listings tracked by Flopper start at $1.99 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA H100 PCIe 80GB

ProviderConfigurationPrice/GPU-hrChecked
RunPod
1× H100 PCIe Community $1.99 4h ago View →
Hyperstack
1× H100 PCIe Spot $2.00 4h ago View →
Hyperstack
1× H100 PCIe $2.50 4h ago View →
RunPod
1× H100 PCIe $2.89 4h ago View →
All H100 PCIe 80GB listings and price history →

NVIDIA H100 NVL 94GB

ProviderConfigurationPrice/GPU-hrChecked
RunPod
1× H100 NVL Community $2.59 4h ago View →
RunPod
1× H100 NVL $3.19 4h ago View →
Microsoft Azure
1× H100 NVL $6.98 4h ago View →
Microsoft Azure
2× H100 NVL $6.98 4h ago View →
Microsoft Azure
1× H100 NVL $6.98 4h ago View →
All H100 NVL 94GB listings and price history →

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.