NVIDIA H100 NVL 94GB
Hopper PCIe 2023 4nm
FP32
60.0
TFLOPS
VRAM
94 GB
HBM3
TDP
400 W
150.0 TFLOPS/kW
Bandwidth
3.9 TB/s
memory
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Description | Bits | Peak TFLOPS | Efficiency |
|---|---|---|---|---|
| INT8 | 8-bit integer | 8 | 1670.5 | 4.176 TFLOPS/W |
| FP8 | 8-bit floating point | 8 | 1670.5 | 4.176 TFLOPS/W |
| FP16 | 16-bit floating point | 16 | 835.5 | 2.089 TFLOPS/W |
| BF16 | Brain Float 16 | 16 | 835.5 | 2.089 TFLOPS/W |
| TF32 | TensorFloat-32 | 32 | 417.5 | 1.044 TFLOPS/W |
| FP32 | 32-bit floating point | 32 | 60.0 | 0.150 TFLOPS/W |
| FP64 | 64-bit floating point | 64 | 30.0 | 0.075 TFLOPS/W |
FP8 Efficiency
4.176 TFLOPS/W
1670.5 TFLOPS / 400W
FP16 Efficiency
2.089 TFLOPS/W
835.5 TFLOPS / 400W
FP32 Efficiency
0.150 TFLOPS/W
60.0 TFLOPS / 400W
Power Specifications
TDP
400 W
Max Power
460 W
Power Connector
PCIe 16-pin
Cooling
Air
Memory Specifications
Capacity
94 GB
Type
HBM3
Bandwidth
3900 GB/s
Interface
--
Hardware & Design
Form Factor
PCIe
Architecture
Hopper
Process Node
4nm
Launch Year
2023
Variant
NVL 94GB
Market Segment
Data Center
Common Use Cases
LLM Training LLM Inference Scientific Computing HPC Workloads
The NVIDIA H100 is optimized for high-performance computing tasks with Hopper architecture delivering 60 TFLOPS of compute power.
Where to Rent
Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.
Browse GPU Cloud ProvidersSimilar GPUs
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
Loading verification...
No spam, unsubscribe anytime.