AMD Radeon Instinct MI300X vs NVIDIA B300

Comparison of AMD Radeon Instinct MI300X with 192 GB HBM3 and 19,456 cores vs NVIDIA B300 with 144 GB HBM3e and 18,944 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI300X outperforms NVIDIA B300 by 30.82% 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 B300

71.9

NVIDIA B300

71.9

Contents:

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

Memory

Memory Size

🔥 +33% 192 ГБ
144 GB ×2 (288 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)

🔥 +52,969% 653.7 TFLOPS
1.2318 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +6% 81.72 TFLOPS
76.99 TFLOPS

FP64 (Double Precision)

🔥 +6,694% 81.72 TFLOPS
1.2029 TFLOPS

CUDA Cores

🔥 +3% 19,456
18,944 ×2 (37888)

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Blackwell Ultra

SM (Streaming Multiprocessor)

No
🔥 148

PCIe Version

PCIe 5.0 x16 PCIe 5.0 x16

ML Software Support

CUDA Version

No 10.3

Clocks & Performance

Base Clock

1,000
🔥 +66% 1,665

Boost Clock

🔥 +3% 2,100
2,032

Memory Clock

🔥 +26% 2,525
2,000

Power Consumption

Recommended PSU

🔥 -36% 1150 W
1800 W

Power Connector

None No

TDP/TGP

🔥 -46% 750 W
1400 W

Rendering

Texture Units (TMU)

🔥 +105% 1,216
592 ×2 (1184)

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 Sept. 11, 2025

Display Outputs

No outputs
No outputs

Renting is cheaper than buying