NVIDIA B300 vs NVIDIA CMP 100HX-210

Comparison of NVIDIA B300 with 144 GB HBM3e and 18,944 cores vs NVIDIA CMP 100HX-210 with 16 GB HBM2 and 5,120 cores.

Loading...

Performance Rating

NVIDIA B300 outperforms NVIDIA CMP 100HX-210 by 471.78% 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 CMP 100HX-210

12.6

NVIDIA CMP 100HX-210

12.6

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)
829.4 GB/s

Memory Bus Width

4,096 бит ×2 (8192 бит) 4,096 бит

ML Performance

FP16 (Half Precision)

1.2318 TFLOPS
🔥 +1,807% 23.49 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +555% 76.99 TFLOPS
11.75 TFLOPS

FP64 (Double Precision)

1.2029 TFLOPS
🔥 +388% 5.873 TFLOPS

CUDA Cores

🔥 +270% 18,944 ×2 (37888)
5,120

RT Cores

No No

Architecture & Compatibility

GPU Architecture

Blackwell Ultra Volta

SM (Streaming Multiprocessor)

🔥 +85% 148
80

PCIe Version

PCIe 5.0 x16 PCIe 1.0 x1

ML Software Support

CUDA Version

🔥 10.3
7.0

Clocks & Performance

Base Clock

🔥 +200% 1,665
555

Boost Clock

🔥 +77% 2,032
1,147

Memory Clock

🔥 +147% 2,000
810

Power Consumption

Recommended PSU

1800 W
🔥 -67% 600 W

Power Connector

No 1x 6-pin + 1x 8-pin

TDP/TGP

1400 W
🔥 -82% 250 W

Rendering

Texture Units (TMU)

🔥 +85% 592 ×2 (1184)
320

ROP

No No

L2 Cache

50 MB
🔥 6 MB

Additional

Slots

🔥 SXM Module
Dual-slot

Release Date

Sept. 11, 2025 March 13, 2020

Display Outputs

No outputs
No outputs

Renting is cheaper than buying