AMD Radeon Instinct MI300X vs GALAX GTX 960 EXOC White

Comparison AMD Radeon Instinct MI300X with 192 GB HBM3 and 19,456 cores vs GALAX GTX 960 EXOC White with 2 GB GDDR5 and 1,024 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI300X outperforms GALAX GTX 960 EXOC White by 4,652.53% 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

GALAX GTX 960 EXOC White

2.0

GALAX GTX 960 EXOC White

2.0

Expert Comparison

AMD Radeon Instinct MI300X значительно превосходит GALAX GTX 960 EXOC по многим параметрам: более мощная архитектура CDNA 3.0, гораздо большее количество ядер и памяти, высокая пропускная способность и FP32-скорость. MI300X предназначена для вычислительных задач и AI, тогда как GTX 960 больше подходит для игр и базовых вычислений.

Contents:

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

Memory

Memory Size

🔥 +9,500% 192 ГБ
2 GB

Memory Type

HBM3 GDDR5

Memory Bandwidth

🔥 10.3 TB/s
112.2 GB/s

Memory Bus Width

8,192 бит 128 бит

ML Performance

FP16 (Half Precision)

🔥 653.7 TFLOPS
No

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +2,819% 81.72 TFLOPS
2.8 TFLOPS

FP64 (Double Precision)

🔥 +93,294% 81.72 TFLOPS
0.0875 TFLOPS

CUDA Cores

🔥 +1,800% 19,456
1,024

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Maxwell 2.0

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 PCIe 3.0 x16

ML Software Support

CUDA Version

No 5.2

CUDA Toolkit (first supported)

v6

CUDA Toolkit (deprecated)

v12

CUDA Toolkit (support removed)

v13

CUDA Toolkit status

Supported Removed

Clocks & Performance

Base Clock

🔥 1,000
1,304

Boost Clock

🔥 +54% 2,100
1,367

Memory Clock

🔥 +44% 2,525
1,753

Power Consumption

Recommended PSU

1150 W
🔥 -74% 300 W

Power Connector

None 1x 8-pin

TDP/TGP

750 W
🔥 -84% 120 W

Rendering

Texture Units (TMU)

🔥 +1,800% 1,216
64

ROP

No No

L2 Cache

🔥 16 MB
1024 KB

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 Dual-slot

Release Date

Dec. 6, 2023 May 5, 2015

Display Outputs

No outputs
1x DVI
1x HDMI 2.0
3x DisplayPort 1.2

2x DVI
1x HDMI 2.0
1x DisplayPort 1.2

Renting is cheaper than buying