AMD Radeon Instinct MI355X vs NVIDIA GeForce RTX 3050 Max-Q Refresh 4 GB

Comparison of AMD Radeon Instinct MI355X with 288 GB HBM3e and 16,384 cores vs NVIDIA GeForce RTX 3050 Max-Q Refresh 4 GB with 4 GB GDDR6 and 2,048 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

AMD Radeon Instinct MI355X

AMD Radeon Instinct MI355X

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

NVIDIA GeForce RTX 3050 Max-Q Refresh 4 GB

NVIDIA GeForce RTX 3050 Max-Q Refresh 4 GB

Contents:

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

Memory

Memory Size

288 GB 4 GB

Memory Type

HBM3e GDDR6

Memory Bandwidth

8.19 TB/s 176.0 GB/s

Memory Bus Width

8,192 бит 128 бит

ML Performance

FP16 (Half Precision)

629.1 TFLOPS 4.608 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

78.64 TFLOPS 4.608 TFLOPS

FP64 (Double Precision)

78.64 TFLOPS 0.072 TFLOPS

CUDA Cores

16,384 2,048

RT Cores

No 16

Architecture & Compatibility

GPU Architecture

CDNA 4.0 Ampere

SM (Streaming Multiprocessor)

No 16

PCIe Version

PCIe 5.0 x16 PCIe 4.0 x8

ML Software Support

CUDA Version

No 8.6

Clocks & Performance

Base Clock

1,000 757

Boost Clock

2,400 1,125

Memory Clock

2,000 1,375

Power Consumption

TDP/TGP

1400 W
🔥 -98% 35 W

Recommended PSU

1800 W No

Power Connector

None None

Rendering

Texture Units (TMU)

1,024 64

ROP

No 16

L2 Cache

32 MB 2 MB

Benchmarks

MLPerf, llama2-70b-99.9 (mxfp4)

10 129 tokens/s

MLPerf, llama3.1-405b (mxfp4)

252.4 tokens/s

Additional

Slots

OAM Module IGP

Release Date

March 12, 2025 July 6, 2022

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying