NVIDIA GeForce GTX 275 vs NVIDIA H200 SXM 141 GB

Comparison of NVIDIA GeForce GTX 275 with 896 GB GDDR3 and 240 cores vs NVIDIA H200 SXM 141 GB with 141 GB HBM3e and 16,896 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

NVIDIA GeForce GTX 275

NVIDIA GeForce GTX 275

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

NVIDIA H200 SXM 141 GB

NVIDIA H200 SXM 141 GB

Contents:

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

Memory

Memory Size

896 MB 141 GB

Memory Type

GDDR3 HBM3e

Memory Bandwidth

127.0 GB/s 4.89 TB/s

Memory Bus Width

448 бит 6,144 бит

ML Performance

FP16 (Half Precision)

No 267.6 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

0.6739 TFLOPS 66.91 TFLOPS

FP64 (Double Precision)

0.0842 TFLOPS 33.45 TFLOPS

CUDA Cores

240 16,896

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Tesla 2.0 Hopper

SM (Streaming Multiprocessor)

30 132

PCIe Version

PCIe 2.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

1.3
🔥 9.0

Clocks & Performance

Base Clock

No 1,500

Boost Clock

No 1,980

Memory Clock

1,134 1,593

Power Consumption

TDP/TGP

🔥 -69% 219 W
700 W

Recommended PSU

🔥 -50% 550 W
1100 W

Power Connector

2x 6-pin 8-pin EPS

Rendering

Texture Units (TMU)

80 528

ROP

No No

L2 Cache

224 KB 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

Dual-slot SXM Module

Release Date

Jan. 15, 2009 Nov. 18, 2024

Display Outputs

2x DVI
No outputs

Renting is cheaper than buying