AMD Radeon Instinct MI300X vs NVIDIA GeForce 820M

Comparison AMD Radeon Instinct MI300X with 192 GB HBM3 and 19,456 cores vs NVIDIA GeForce 820M with 1,024 GB DDR3 and 96 cores.

Loading...

Performance Rating

AMD Radeon Instinct MI300X outperforms NVIDIA GeForce 820M by 11,517.28% 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 GeForce 820M

0.8

NVIDIA GeForce 820M

0.8

Expert Comparison

AMD Radeon Instinct MI300X значительно превосходит NVIDIA GeForce 820M по всем параметрам. MI300X имеет гораздо больше ядер и памяти, более высокую пропускную способность и вычислительную мощность. Он предназначен для вычислительных задач и обработки больших данных, в то время как GeForce 820M устарел и подходит только для легких задач в ноутбуках.

Contents:

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

Memory

Memory Size

🔥 192 ГБ
1,024 MB

Memory Type

HBM3 DDR3

Memory Bandwidth

🔥 10.3 TB/s
14.40 GB/s

Memory Bus Width

8,192 бит 64 бит

ML Performance

FP16 (Half Precision)

🔥 653.7 TFLOPS
No

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +33,950% 81.72 TFLOPS
0.24 TFLOPS

FP64 (Double Precision)

🔥 +408,500% 81.72 TFLOPS
0.02 TFLOPS

CUDA Cores

🔥 +20,167% 19,456
96

RT Cores

No No

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Fermi 2.0

SM (Streaming Multiprocessor)

No 2

PCIe Version

PCIe 5.0 x16 PCIe 2.0 x16

ML Software Support

CUDA Version

No 2.1

CUDA Toolkit (first supported)

v3

CUDA Toolkit (deprecated)

v8

CUDA Toolkit (support removed)

v9

CUDA Toolkit status

Supported Removed

Clocks & Performance

Base Clock

🔥 1,000
No

Boost Clock

🔥 2,100
No

Memory Clock

🔥 +181% 2,525
900

Power Consumption

Recommended PSU

1150 W No

Power Connector

None None

TDP/TGP

750 W
🔥 -98% 15 W

Rendering

Texture Units (TMU)

🔥 +7,500% 1,216
16

ROP

No No

L2 Cache

🔥 16 MB
128 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 IGP

Release Date

Dec. 6, 2023 Nov. 27, 2013

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying