NVIDIAVendor documented

H200 SXM

Hopper · Hopper (refresh) · SXM5 · 2024

H100 compute with 141 GB HBM3e and 4.8 TB/s. The extra memory notably improves long-context and larger-model inference.

LLM trainingLLM inferenceRAGMultimodalHPC
Precision fingerprint
6432t3216BF168i8
Memory

141 GB

HBM3e

Bandwidth

4.8 TB/s

peak

TDP

700 W

air or liquid

Max model

~55B

FP16, planning est.

Compute throughput

FP6467 TFLOPS
FP3267 TFLOPS
TF32494 TFLOPS
FP16989 TFLOPS
BF16989 TFLOPS
FP81.98 PFLOPS
INT81.98 PFLOPS

Platform & software

InterconnectNVLink 4 — 900 GB/s
PCIePCIe 5.0 x16
Coolingair or liquid
MIGSupported
PartitioningUp to 7× MIG
VirtualizationvGPU, MIG
FrameworksCUDA, TensorRT-LLM, Triton, NeMo, vLLM
AvailabilityAWS, Azure, GCP, OCI, bare-metal
Known limitations
  • ·Same compute as H100 — gains are memory capacity and bandwidth only
Related GPUs
NVIDIA

H100 SXM5

80 GB · 989 TFLOPS FP16

NVIDIA

H100 PCIe

80 GB · 756 TFLOPS FP16

NVIDIA

H100 NVL

94 GB · 989 TFLOPS FP16