AMD Radeon Instinct MI250 vs NVIDIA B100

Comparison of AMD Radeon Instinct MI250 with 128 GB HBM2e and 13,312 cores vs NVIDIA B100 with 96 GB HBM3e and 16,896 cores.

Loading...

Performance Rating

NVIDIA B100 outperforms AMD Radeon Instinct MI250 by 11.18% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI250

50.9

AMD Radeon Instinct MI250

50.9
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

NVIDIA B100

56.6

NVIDIA B100

56.6

Contents:

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

Memory

Memory Size

🔥 +33% 128 ГБ
96 ГБ ×2 (192 ГБ)

Memory Type

HBM2e HBM3e

Memory Bandwidth

3.28 TB/s
🔥 +25% 4.10 TB/s ×2 (8.2 TB/s)

Memory Bus Width

8,192 бит 4,096 бит ×2 (8192 бит)

ML Performance

FP16 (Half Precision)

🔥 +46% 362.1 TFLOPS
248.3 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

45.26 TFLOPS
🔥 +37% 62.08 TFLOPS

FP64 (Double Precision)

🔥 +46% 45.26 TFLOPS
31.04 TFLOPS

CUDA Cores

13,312
🔥 +27% 16,896 ×2 (33792)

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 2.0 Blackwell

SM (Streaming Multiprocessor)

No
🔥 132

PCIe Version

PCIe 4.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No 10.1

Clocks & Performance

Base Clock

1,000
🔥 +66% 1,665

Boost Clock

1,700
🔥 +8% 1,837

Memory Clock

1,600
🔥 +25% 2,000

Power Consumption

TDP/TGP

🔥 -50% 500 W
1000 W

Recommended PSU

🔥 -36% 900 W
1400 W

Power Connector

2x 8-pin No

Rendering

Texture Units (TMU)

🔥 +58% 832
528 ×2 (1056)

ROP

No No

L2 Cache

16 MB
🔥 +212% 50 MB

Benchmarks

llama.cpp, llama-2-7b-Q4_0

63.9 tokens/s

Additional

Slots

Dual-slot
🔥 SXM Module

Release Date

Nov. 8, 2021 Nov. 17, 2024

Display Outputs

No outputs
No outputs

Renting is cheaper than buying