AMD Radeon Pro Vega 64X vs NVIDIA H200 SXM 141 GB

Comparison of AMD Radeon Pro Vega 64X with 16 GB HBM2 and 4,096 cores vs NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores.

Loading...

Performance Rating

NVIDIA H200 SXM 141 GB outperforms AMD Radeon Pro Vega 64X by 524.47% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Pro Vega 64X

10.8

AMD Radeon Pro Vega 64X

10.8
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA H200 SXM 141 GB

67.4

NVIDIA H200 SXM 141 GB

67.4

Contents:

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

Memory

Memory Size

16 GB
🔥 +781% 141 ГБ

Memory Type

HBM2 HBM3e

Memory Bandwidth

512.0 GB/s
🔥 4.89 TB/s

Memory Bus Width

2,048 бит 6,144 бит

ML Performance

FP16 (Half Precision)

24.05 TFLOPS
🔥 +1,013% 267.6 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

12.03 TFLOPS
🔥 +456% 66.91 TFLOPS

FP64 (Double Precision)

0.7516 TFLOPS
🔥 +4,351% 33.45 TFLOPS

CUDA Cores

4,096
🔥 +312% 16,896

RT Cores

No No

Architecture & Compatibility

GPU Architecture

GCN 5.0 Hopper

SM (Streaming Multiprocessor)

No
🔥 132

PCIe Version

PCIe 3.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No 9.0

Clocks & Performance

Base Clock

1,250
🔥 +20% 1,500

Boost Clock

1,468
🔥 +35% 1,980

Memory Clock

1,000
🔥 +59% 1,593

Power Consumption

Recommended PSU

No 1100 W

Power Connector

None 8-pin EPS

TDP/TGP

🔥 -64% 250 W
700 W

Rendering

Texture Units (TMU)

256
🔥 +106% 528

ROP

No No

L2 Cache

4 MB
🔥 +1,150% 50 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

IGP
🔥 SXM Module

Release Date

March 19, 2019 Nov. 18, 2024

Display Outputs

Portable Device Dependent
No outputs

Renting is cheaper than buying