NVIDIA B300 vs NVIDIA P106M

Comparison NVIDIA B300 with 144 GB HBM3e and 18,944 cores vs NVIDIA P106M with 4 GB GDDR5 and 1,152 cores.

Loading...

Performance Rating

NVIDIA B300 outperforms NVIDIA P106M by 3,169.55% 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 P106M

2.2

NVIDIA P106M

2.2

Expert Comparison

NVIDIA B300 значительно превосходит NVIDIA P106M по многим параметрам. У B300 больше ядер, большая память и шина, а также гораздо более высокая пропускная способность и вычислительная мощность. B300 подходит для сложных вычислений и графики, в то время как P106M более подходящий для базовых задач и не требует больших энергетических затрат.

Contents:

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

Memory

Memory Size

🔥 +3,500% 144 ГБ ×2 (288 ГБ)
4 GB

Memory Type

HBM3e GDDR5

Memory Bandwidth

🔥 4.10 TB/s ×2 (8.2 TB/s)
96.13 GB/s

Memory Bus Width

4,096 бит ×2 (8192 бит) 128 бит

ML Performance

FP16 (Half Precision)

🔥 +2,549% 1.2318 TFLOPS
0.0465 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +2,489% 76.99 TFLOPS
2.974 TFLOPS

FP64 (Double Precision)

🔥 +1,193% 1.2029 TFLOPS
0.093 TFLOPS

CUDA Cores

🔥 +1,544% 18,944 ×2 (37888)
1,152

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Blackwell Ultra Pascal

SM (Streaming Multiprocessor)

🔥 +1,544% 148
9

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

🔥 10.3
6.1

CUDA Toolkit (first supported)

v12 v8

CUDA Toolkit (deprecated)

v12

CUDA Toolkit (support removed)

v13

CUDA Toolkit status

Supported Removed

Clocks & Performance

Base Clock

🔥 +29% 1,665
1,291

Boost Clock

🔥 +57% 2,032
1,291

Memory Clock

🔥 +33% 2,000
1,502

Power Consumption

Recommended PSU

1800 W No

Power Connector

No None

TDP/TGP

1400 W
🔥 -95% 75 W

Rendering

Texture Units (TMU)

🔥 +722% 592 ×2 (1184)
72

ROP

No No

L2 Cache

🔥 50 MB
1280 KB

Additional

Slots

🔥 SXM Module
MXM Module

Release Date

Sept. 11, 2025 Jan. 23, 2019

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying