NVIDIA B300 vs NVIDIA CMP 70HX

Comparison of NVIDIA B300 with 144 GB HBM3e and 18,944 cores vs NVIDIA CMP 70HX with 8 GB GDDR6X and 3,840 cores.

Loading...

Performance Rating

NVIDIA B300 outperforms NVIDIA CMP 70HX by 837.81% 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 70HX

7.7

NVIDIA CMP 70HX

7.7

Contents:

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

Memory

Memory Size

🔥 +1,700% 144 ГБ ×2 (288 ГБ)
8 GB

Memory Type

HBM3e GDDR6X

Memory Bandwidth

🔥 4.10 TB/s ×2 (8.2 TB/s)
608.3 GB/s

Memory Bus Width

4,096 бит ×2 (8192 бит) 256 бит

ML Performance

FP16 (Half Precision)

1.2318 TFLOPS
🔥 +769% 10.71 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +619% 76.99 TFLOPS
10.71 TFLOPS

FP64 (Double Precision)

🔥 +619% 1.2029 TFLOPS
0.1674 TFLOPS

CUDA Cores

🔥 +393% 18,944 ×2 (37888)
3,840

RT Cores

No
🔥 30

Architecture & Compatibility

GPU Architecture

Blackwell Ultra Ampere

SM (Streaming Multiprocessor)

🔥 +393% 148
30

PCIe Version

PCIe 5.0 x16 PCIe 1.0 x4

ML Software Support

CUDA Version

🔥 10.3
8.6

Clocks & Performance

Base Clock

🔥 +22% 1,665
1,365

Boost Clock

🔥 +46% 2,032
1,395

Memory Clock

🔥 +68% 2,000
1,188

Power Consumption

Recommended PSU

1800 W
🔥 -89% 200 W

Power Connector

No 1x 12-pin

TDP/TGP

1400 W unknown

Rendering

Texture Units (TMU)

🔥 +393% 592 ×2 (1184)
120

ROP

No
🔥 30

L2 Cache

🔥 +1,150% 50 MB
4 MB

Additional

Slots

🔥 SXM Module
Dual-slot

Release Date

Sept. 11, 2025 March 11, 2021

Display Outputs

No outputs
No outputs

Renting is cheaper than buying