AMD Radeon Instinct MI325X vs Intel Arc B390

Comparison of AMD Radeon Instinct MI325X with 288 GB HBM3e and 19,456 cores vs Intel Arc B390 and 1,536 cores.

Loading...

Performance Rating

A100 A100
H200 H200
MI325X MI325X

AMD Radeon Instinct MI325X

100.0

AMD Radeon Instinct MI325X

100.0
RX 7900 XTX RX 7900 XTX
MI250 MI250
Instinct MI300X Instinct MI300X

Intel Arc B390

Intel Arc B390

Contents:

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

Memory

Memory Size

🔥 288 ГБ
No

Memory Type

HBM3e System Shared

Memory Bandwidth

🔥 10.3 TB/s
System Dependent

Memory Bus Width

8,192 бит No

ML Performance

FP16 (Half Precision)

🔥 +4,156% 653.7 TFLOPS
15.36 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 +964% 81.72 TFLOPS
7.68 TFLOPS

FP64 (Double Precision)

🔥 +8,413% 81.72 TFLOPS
0.96 TFLOPS

CUDA Cores

🔥 +1,167% 19,456
1,536

RT Cores

No 12

Architecture & Compatibility

GPU Architecture

CDNA 3.0 Xe3-LPG

SM (Streaming Multiprocessor)

No No

PCIe Version

PCIe 5.0 x16 IGP

ML Software Support

CUDA Version

No No

Clocks & Performance

Base Clock

🔥 +233% 1,000
300

Boost Clock

🔥 2,100
2,500

Memory Clock

🔥 2,525
No

Power Consumption

TDP/TGP

1000 W
🔥 -92% 80 W

Recommended PSU

1400 W No

Power Connector

None None

Rendering

Texture Units (TMU)

🔥 +2,433% 1,216
48

ROP

No 12

L2 Cache

🔥 16 MB
16 MB

Benchmarks

MLPerf, llama2-70b-99.9 (Dummy)

3 596 tokens/s

MLPerf, llama2-70b-99.9 (fp8)

1 946 tokens/s

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

22.4 tokens/s

MLPerf, mixtral-8x7b (fp8)

6 975 tokens/s

Additional

Slots

OAM Module IGP

Release Date

Oct. 15, 2024 Jan. 27, 2026

Display Outputs

No outputs
Portable Device Dependent

Renting is cheaper than buying