NVIDIA H200 SXM 141 GB vs NVIDIA Jetson AGX Orin 32 GB

Comparison of NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores vs NVIDIA Jetson AGX Orin 32 GB with 32 GB LPDDR5 and 1,792 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA H200 SXM 141 GB

NVIDIA H200 SXM 141 GB

RX 7900 XTX RX 7900 XTX
Instinct MI300X Instinct MI300X
MI250 MI250

NVIDIA Jetson AGX Orin 32 GB

NVIDIA Jetson AGX Orin 32 GB

Contents:

Memory ML Performance Compute Power Architecture & Compatibility ML Software Support Clocks & Performance Power Consumption Rendering Benchmarks Additional

Memory

Memory Size

141 GB 32 GB

Memory Type

HBM3e LPDDR5

Memory Bandwidth

4.89 TB/s 204.8 GB/s

Memory Bus Width

6,144 бит 256 бит

ML Performance

FP16 (Half Precision)

267.6 TFLOPS 6.666 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

66.91 TFLOPS 3.333 TFLOPS

FP64 (Double Precision)

33.45 TFLOPS No

CUDA Cores

16,896 1,792

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Hopper Ampere

SM (Streaming Multiprocessor)

132 14

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x4

ML Software Support

CUDA Version

🔥 9.0
8.7

Clocks & Performance

Base Clock

1,500 No

Boost Clock

1,980 No

Memory Clock

1,593 800

Power Consumption

TDP/TGP

700 W
🔥 -94% 40 W

Recommended PSU

1100 W No

Power Connector

8-pin EPS No

Rendering

Texture Units (TMU)

528 56

ROP

No No

L2 Cache

50 MB 6 MB

Benchmarks

MLPerf, llama2-70b-99.9 (UNSET)

3 534 tokens/s

MLPerf, llama2-70b-99.9 (fp16)

3 553 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

2 444 tokens/s

MLPerf, llama3.1-405b (fp16)

40.8 tokens/s

MLPerf, llama3.1-405b (fp8)

25.3 tokens/s

MLPerf, llama3.1-8b (fp8)

5 161 tokens/s

MLPerf, deepseek-r1 (fp8)

1 113 tokens/s

MLPerf, mixtral-8x7b (fp8)

7 132 tokens/s

Additional

Slots

SXM Module IGP

Release Date

Nov. 18, 2024 Feb. 11, 2023

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying