NVIDIA GeForce RTX 5090 Mobile vs NVIDIA H100 PCIe 80 GB

Comparison of NVIDIA GeForce RTX 5090 Mobile with 24 GB GDDR7 and 10,496 cores vs NVIDIA H100 PCIe 80 GB with 80 GB HBM2e and 14,592 cores.

Loading...

Performance Rating

NVIDIA H100 PCIe 80 GB outperforms NVIDIA GeForce RTX 5090 Mobile by 140.58% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA GeForce RTX 5090 Mobile

18.3

NVIDIA GeForce RTX 5090 Mobile

18.3
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA H100 PCIe 80 GB

44.1

NVIDIA H100 PCIe 80 GB

44.1

Contents:

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

Memory

Memory Size

24 GB
🔥 +233% 80 ГБ

Memory Type

GDDR7 HBM2e

Memory Bandwidth

896.0 GB/s
🔥 2.04 TB/s

Memory Bus Width

256 бит 5,120 бит

ML Performance

FP16 (Half Precision)

33.52 TFLOPS
🔥 +511% 204.9 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

33.52 TFLOPS
🔥 +53% 51.22 TFLOPS

FP64 (Double Precision)

0.5238 TFLOPS
🔥 +4,789% 25.61 TFLOPS

CUDA Cores

10,496
🔥 +39% 14,592

RT Cores

🔥 82
No

Architecture & Compatibility

GPU Architecture

Blackwell 2.0 Hopper

SM (Streaming Multiprocessor)

82
🔥 +39% 114

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

🔥 12.0
9.0

Clocks & Performance

Base Clock

1,095 1,095

Boost Clock

1,597
🔥 +10% 1,755

Memory Clock

🔥 +10% 1,750
1,593

Power Consumption

Recommended PSU

No 750 W

Power Connector

None 1x 16-pin

TDP/TGP

🔥 -73% 95 W
350 W

Rendering

Texture Units (TMU)

328
🔥 +39% 456

ROP

🔥 82
No

L2 Cache

🔥 +28% 64 MB
50 MB

Benchmarks

MLPerf, llama2-70b-99.9 (fp8)

1 222 tokens/s

MLPerf, mixtral-8x7b (fp8)

3 466 tokens/s

Additional

Slots

IGP Dual-slot

Release Date

March 27, 2025 Oct. 13, 2022

Display Outputs

Portable Device Dependent
No outputs

Renting is cheaper than buying