Rubin Ultra GPU vs Radeon Instinct MI350P

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	CDNA 4.0 (2025−2026)	Rubin Ultra (2027)
GPU code name	MI350 128CU	GR110
Market segment	Workstation	Workstation
Release date	7 May 2026 (less than a year ago)	2027

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	8192	57344
Core clock speed	1000 MHz	700 MHz
Boost clock speed	2200 MHz	2267 MHz
Number of transistors	73,000 million	670,000 million
Manufacturing process technology	3 nm	3 nm
Power consumption (TDP)	600 Watt	3600 Watt
Texture fill rate	1,126.4	4,062.5
Floating-point processing power	36.04 TFLOPS	260 TFLOPS
ROPs	no data	24
TMUs	512	1792
Tensor Cores	no data	1792
L1 Cache	2 MB	112 MB
L2 Cache	16 MB	128 MB
L3 Cache	128 MB	no data

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 5.0 x16	PCIe 6.0 x16
Length	267 mm	no data
Width	2-slot	SXM Module
Supplementary power connectors	1x 16-pin	no data

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	HBM3e	HBM4e
Maximum RAM amount	144 GB	1024 GB
Memory bus width	8192 Bit	32768 Bit
Memory clock speed	2000 MHz	1900 MHz
Memory bandwidth	8.19 TB/s	31.1 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	-	10.7
DLSS	-	+

Pros & cons summary

---

Maximum RAM amount	144 GB	1024 GB
Power consumption (TDP)	600 Watt	3600 Watt