H100 SXM5 vs Radeon 660M

Primary details

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

Place in the ranking	587	not rated
Place by popularity	not in top-100	not in top-100
Power efficiency	14.58	no data
Architecture	RDNA 2.0 (2020−2025)	Hopper (2022−2024)
GPU code name	Rembrandt+	GH100
Market segment	Laptop	Workstation
Release date	3 January 2023 (3 years ago)	22 March 2022 (4 years ago)

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	384	8448
Core clock speed	1500 MHz	1065 MHz
Boost clock speed	1900 MHz	1780 MHz
Number of transistors	13,100 million	80,000 million
Manufacturing process technology	6 nm	4 nm
Power consumption (TDP)	40 Watt	700 Watt
Texture fill rate	45.60	939.8
Floating-point processing power	1.459 TFLOPS	30.07 TFLOPS
ROPs	16	24
TMUs	24	528
Tensor Cores	no data	528
Ray Tracing Cores	6	no data
L0 Cache	96 KB	no data
L1 Cache	128 KB	24.8 MB
L2 Cache	2 MB	50 MB
L3 Cache	8 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 4.0 x8	PCIe 5.0 x16
Supplementary power connectors	None	8-pin EPS

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	System Shared	HBM3
Maximum RAM amount	System Shared	80 GB
Memory bus width	System Shared	5120 Bit
Memory clock speed	System Shared	1500 MHz
Memory bandwidth	no data	1,920 GB/s
Shared memory	+	-
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

Portable Device Dependent

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	6.7	N/A
OpenGL	4.6	N/A
OpenCL	2.0	3.0
Vulkan	1.3	N/A
CUDA	-	9.0
DLSS	-	+

Pros & cons summary

---

Recency	3 January 2023	22 March 2022
Chip lithography	6 nm	4 nm
Power consumption (TDP)	40 Watt	700 Watt