AMD Radeon 880M vs NVIDIA H200 SXM 141 GB

Comparison of AMD Radeon 880M and 768 cores vs NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores.

Loading...

Performance Rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon 880M

0.0

AMD Radeon 880M

0.0
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

No
🔥 141 ГБ

Memory Type

System Shared HBM3e

Memory Bandwidth

System Dependent
🔥 4.89 TB/s

Memory Bus Width

No 6,144 бит

ML Performance

FP16 (Half Precision)

8.909 TFLOPS
🔥 +2,904% 267.6 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

4.454 TFLOPS
🔥 +1,402% 66.91 TFLOPS

FP64 (Double Precision)

0.2784 TFLOPS
🔥 +11,915% 33.45 TFLOPS

CUDA Cores

768
🔥 +2,100% 16,896

RT Cores

🔥 12
No

Architecture & Compatibility

GPU Architecture

RDNA 3.5 Hopper

SM (Streaming Multiprocessor)

No
🔥 132

PCIe Version

PCIe 4.0 x8 PCIe 5.0 x16

ML Software Support

CUDA Version

No 9.0

Clocks & Performance

Base Clock

400
🔥 +275% 1,500

Boost Clock

🔥 +46% 2,900
1,980

Memory Clock

No
🔥 1,593

Power Consumption

TDP/TGP

🔥 -98% 15 W
700 W

Recommended PSU

No 1100 W

Power Connector

None 8-pin EPS

Rendering

Texture Units (TMU)

48
🔥 +1,000% 528

ROP

🔥 12
No

L2 Cache

2 MB
🔥 +2,400% 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

July 15, 2024 Nov. 18, 2024

Display Outputs

Portable Device Dependent
No outputs

Renting is cheaper than buying