Radeon Instinct MI455X vs PG506-232

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the ranking	not rated	not rated
Place by popularity	not in top-100	not in top-100
Architecture	Ampere (2020−2025)	CDNA 5.0 (2026)
GPU code name	GA100	MI450 256CU
Market segment	Workstation	Workstation
Release date	12 April 2021 (5 years ago)	23 July 2026 (recently)

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.

Pipelines / CUDA cores	3584	32768
Core clock speed	930 MHz	1000 MHz
Boost clock speed	1440 MHz	2400 MHz
Number of transistors	54,200 million	320,000 million
Manufacturing process technology	7 nm	2 nm
Power consumption (TDP)	165 Watt	1400 Watt
Texture fill rate	322.6	2,457.6
Floating-point processing power	10.32 TFLOPS	157.3 TFLOPS
ROPs	96	no data
TMUs	224	1024
Tensor Cores	224	no data
L1 Cache	10.5 MB	8 MB
L2 Cache	24 MB	192 MB

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface	PCIe 4.0 x16	PCIe 5.0 x16
Length	267 mm	no data
Width	2-slot	EAM Module
Supplementary power connectors	8-pin EPS	None

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	HBM2	HBM4
Maximum RAM amount	24 GB	432 GB
Memory bus width	3072 Bit	24576 Bit
Memory clock speed	1215 MHz	1900 MHz
Memory bandwidth	933.1 GB/s	23.3 TB/s
Resizable BAR	+	+

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display Connectors

No outputs

No outputs

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	N/A	N/A
Shader Model	N/A	N/A
OpenGL	N/A	N/A
OpenCL	3.0	3.0
Vulkan	N/A	N/A
CUDA	8.0	-
DLSS	+	-

Pros & cons summary

---

Recency	12 April 2021	23 July 2026
Maximum RAM amount	24 GB	432 GB
Chip lithography	7 nm	2 nm
Power consumption (TDP)	165 Watt	1400 Watt