Rubin Ultra GPU vs L4

Primary details

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

Place in the ranking	249	not rated
Place by popularity	not in top-100	not in top-100
Power efficiency	27.85	no data
Architecture	Ada Lovelace (2022−2024)	Rubin Ultra (2027)
GPU code name	AD104	GR110
Market segment	Workstation	Workstation
Release date	21 March 2023 (3 years 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	7424	57344
Core clock speed	795 MHz	700 MHz
Boost clock speed	2040 MHz	2267 MHz
Number of transistors	35,800 million	670,000 million
Manufacturing process technology	5 nm	3 nm
Power consumption (TDP)	72 Watt	3600 Watt
Texture fill rate	489.6	4,062.5
Floating-point processing power	30.29 TFLOPS	260 TFLOPS
ROPs	80	24
TMUs	240	1792
Tensor Cores	240	1792
Ray Tracing Cores	60	no data
L1 Cache	7.5 MB	112 MB
L2 Cache	48 MB	128 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 6.0 x16
Length	169 mm	no data
Width	1-slot	SXM Module
Supplementary power connectors	None	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	GDDR6	HBM4e
Maximum RAM amount	24 GB	1024 GB
Memory bus width	192 Bit	32768 Bit
Memory clock speed	1563 MHz	1900 MHz
Memory bandwidth	300.1 GB/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	12 Ultimate (12_2)	N/A
Shader Model	6.8	N/A
OpenGL	4.6	N/A
OpenCL	3.0	3.0
Vulkan	1.3	N/A
CUDA	8.9	10.7
DLSS	+	+

Pros & cons summary

---

Maximum RAM amount	24 GB	1024 GB
Chip lithography	5 nm	3 nm
Power consumption (TDP)	72 Watt	3600 Watt