NVIDIA B300 vs NVIDIA Tesla P100 SXM2

Comparison of NVIDIA B300 with 144 GB HBM3e and 18,944 cores vs NVIDIA Tesla P100 SXM2 with 16 GB HBM2 and 3,584 cores.

Loading...

Performance Rating

NVIDIA B300 outperforms NVIDIA Tesla P100 SXM2 by 520.09% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

NVIDIA B300

71.9

NVIDIA B300

71.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA Tesla P100 SXM2

11.6

NVIDIA Tesla P100 SXM2

11.6

Contents:

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

Memory

Memory Size

🔥 +800% 144 ГБ ×2 (288 ГБ)
16 GB

Memory Type

HBM3e HBM2

Memory Bandwidth

🔥 4.10 TB/s ×2 (8.2 TB/s)
732.2 GB/s

Memory Bus Width

4,096 бит ×2 (8192 бит) 4,096 бит

ML Performance

FP16 (Half Precision)

🔥 1.2318 TFLOPS
21.22 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +626% 76.99 TFLOPS
10.61 TFLOPS

FP64 (Double Precision)

🔥 1.2029 TFLOPS
5.304 TFLOPS

CUDA Cores

🔥 +429% 18,944 ×2 (37888)
3,584

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Blackwell Ultra Pascal

SM (Streaming Multiprocessor)

🔥 +164% 148
56

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

🔥 10.3
6.0

Clocks & Performance

Base Clock

🔥 +25% 1,665
1,328

Boost Clock

🔥 +37% 2,032
1,480

Memory Clock

🔥 +180% 2,000
715

Power Consumption

Recommended PSU

1800 W
🔥 -61% 700 W

Power Connector

No None

TDP/TGP

1400 W
🔥 -79% 300 W

Rendering

Texture Units (TMU)

🔥 +164% 592 ×2 (1184)
224

ROP

No No

L2 Cache

🔥 +1,150% 50 MB
4 MB

Additional

Slots

SXM Module SXM Module

Release Date

Sept. 11, 2025 April 5, 2016

Display Outputs

No outputs
No outputs

Renting is cheaper than buying