MAXSUN Arc B580 Milestone vs NVIDIA RTX PRO 6000 Blackwell

Comparison of MAXSUN Arc B580 Milestone with 12 GB GDDR6 and 2,560 cores vs NVIDIA RTX PRO 6000 Blackwell with 96 GB GDDR7 and 24,064 cores.

Loading...

Performance Rating

H200 H200
MI325X MI325X
A100 A100

MAXSUN Arc B580 Milestone

8.9

MAXSUN Arc B580 Milestone

8.9
RX 7900 XTX RX 7900 XTX
Instinct MI300X Instinct MI300X
MI250 MI250

NVIDIA RTX PRO 6000 Blackwell

NVIDIA RTX PRO 6000 Blackwell

Contents:

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

Memory

Memory Size

🔥 12 ГБ
96 GB

Memory Type

GDDR6 GDDR7

Memory Bandwidth

456.0 GB/s 1.79 TB/s

Memory Bus Width

192 бит 512 бит

ML Performance

FP16 (Half Precision)

🔥 29.18 TFLOPS
126.0 TFLOPS

BF16 (Brain Float)

No No

TF32 (TensorFloat)

No No

Compute Power

FP32 (Single Precision)

🔥 14.59 TFLOPS
126.0 TFLOPS

FP64 (Double Precision)

🔥 1.824 TFLOPS
1.968 TFLOPS

CUDA Cores

🔥 2,560
24,064

RT Cores

🔥 20
188

Architecture & Compatibility

GPU Architecture

Xe2 Blackwell 2.0

SM (Streaming Multiprocessor)

No 188

PCIe Version

PCIe 4.0 x8 PCIe 5.0 x16

ML Software Support

CUDA Version

No 12.0

Clocks & Performance

Base Clock

🔥 +68% 2,670
1,590

Boost Clock

🔥 +9% 2,850
2,617

Memory Clock

🔥 +36% 2,375
1,750

Power Consumption

TDP/TGP

🔥 -68% 190 W
600 W

Recommended PSU

🔥 -55% 450 W
1000 W

Power Connector

1x 8-pin 1x 16-pin

Rendering

Texture Units (TMU)

🔥 160
752

ROP

🔥 20
188

L2 Cache

🔥 18 MB
128 MB

Benchmarks

llama.cpp, llama 7B Q4_0

104.4 tokens/s

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

104.4 tokens/s

Geekbench AI, FP16

54 886 points

Geekbench AI, INT8

28 552 points

Geekbench AI, FP32

38 105 points

Additional

Slots

Dual-slot Dual-slot

Release Date

Dec. 13, 2024 March 18, 2025

Display Outputs

1x HDMI 2.1a
3x DisplayPort 2.1
4x DisplayPort 2.1b

Renting is cheaper than buying