Radeon Instinct MI455X vs P106-090

Primary details

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

Place in the ranking	629	not rated
Place by popularity	not in top-100	not in top-100
Power efficiency	6.65	no data
Architecture	Pascal (2016−2021)	CDNA 5.0 (2026)
GPU code name	GP106	MI450 256CU
Market segment	Workstation	Workstation
Release date	31 July 2017 (8 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	768	32768
Core clock speed	1354 MHz	1000 MHz
Boost clock speed	1531 MHz	2400 MHz
Number of transistors	4,400 million	320,000 million
Manufacturing process technology	16 nm	2 nm
Power consumption (TDP)	75 Watt	1400 Watt
Texture fill rate	73.49	2,457.6
Floating-point processing power	2.352 TFLOPS	157.3 TFLOPS
ROPs	48	no data
TMUs	48	1024
L1 Cache	288 KB	8 MB
L2 Cache	1536 KB	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 1.0 x1	PCIe 5.0 x16
Length	250 mm	no data
Width	2-slot	EAM Module
Supplementary power connectors	1x 6-pin	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	GDDR5	HBM4
Maximum RAM amount	3 GB	432 GB
Memory bus width	192 Bit	24576 Bit
Memory clock speed	2002 MHz	1900 MHz
Memory bandwidth	192.2 GB/s	23.3 TB/s

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	12 (12_1)	N/A
Shader Model	6.8	N/A
OpenGL	4.6	N/A
OpenCL	3.0	3.0
Vulkan	1.3	N/A
CUDA	6.1	-

Pros & cons summary

---

Recency	31 July 2017	23 July 2026
Maximum RAM amount	3 GB	432 GB
Chip lithography	16 nm	2 nm
Power consumption (TDP)	75 Watt	1400 Watt