AMD Radeon Instinct MI300X vs NVIDIA B100

Comparison of AMD Radeon Instinct MI300X with 192 GB HBM3 and 19,456 cores vs NVIDIA B100 with 96 GB HBM3e and 16,896 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI300X outperforms NVIDIA B100 by 66.31% in the overall GPU ARK performance rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI300X

94.1

AMD Radeon Instinct MI300X

94.1
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

🔥 +100% 192 ГБ
96 ГБ ×2 (192 ГБ)

Memory Type

HBM3 HBM3e

Memory Bandwidth

🔥 +151% 10.3 TB/s
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)

🔥 +163% 653.7 TFLOPS
248.3 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +32% 81.72 TFLOPS
62.08 TFLOPS

FP64 (Double Precision)

🔥 +163% 81.72 TFLOPS
31.04 TFLOPS

CUDA Cores

🔥 +15% 19,456
16,896 ×2 (33792)

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Blackwell

SM (Streaming Multiprocessor)

No
🔥 132

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No 10.1

Clocks & Performance

Base Clock

1,000
🔥 +66% 1,665

Boost Clock

🔥 +14% 2,100
1,837

Memory Clock

🔥 +26% 2,525
2,000

Power Consumption

TDP/TGP

🔥 -25% 750 W
1000 W

Recommended PSU

🔥 -18% 1150 W
1400 W

Power Connector

None No

Rendering

Texture Units (TMU)

🔥 +130% 1,216
528 ×2 (1056)

ROP

No No

L2 Cache

16 MB
🔥 +212% 50 MB

Benchmarks

MLPerf, llama2-70b-99.9 (UNSET)

1 983 tokens/s

MLPerf, llama2-70b-99.9 (fp16)

1 740 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

1 057 tokens/s

MLPerf, llama3.1-405b (UNSET)

30.4 tokens/s

MLPerf, llama3.1-405b (fp16)

34.8 tokens/s

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

232.9 tokens/s

MLPerf, mixtral-8x7b (fp8)

5 975 tokens/s

Additional

Slots

OAM Module
🔥 SXM Module

Release Date

Dec. 6, 2023 Nov. 17, 2024

Display Outputs

No outputs
No outputs

Renting is cheaper than buying