H100 PCIe vs GeForce RTX 3070 Ti

General info

Comparison of graphics card architecture, market segment, value for money and other general parameters.

Place in performance rating	14	not rated
Place by popularity	50	no data
Value for money	37.99	no data
Architecture	Ampere (2020−2022)	Hopper (2022)
GPU code name	Ampere GA104	GH100
Market segment	Desktop	Desktop
Release date	31 May 2021 (1 year old)	22 March 2022 (less than a year old)
Launch price (MSRP)	$599	no data
Current price	$762 (1.3x MSRP)	no data

Technical specs

General performance parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. These parameters indirectly speak of performance, but for precise assessment you have to consider their benchmark and gaming test results. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores	6144	7296
Core clock speed	1575 MHz	no data
Boost clock speed	1770 MHz	1650 MHz
Number of transistors	17,400 million	80,000 million
Manufacturing process technology	8 nm	4 nm
Thermal design power (TDP)	290 Watt	350 Watt
Texture fill rate	339.8	752.4

Compatibility, dimensions and requirements

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop video 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	267 mm
Width	2-slot	2-slot
Supplementary power connectors	1x 12-pin	8-pin EPS

Memory

Parameters of memory installed: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors have no dedicated VRAM and use a shared part of system RAM.

Memory type	GDDR6	HBM2e
Maximum RAM amount	8 GB	80 GB
Memory bus width	256 Bit	5120 Bit
Memory clock speed	19000 MHz	2 GB/s
Memory bandwidth	608.3 GB/s	1,280 GB/s
Shared memory	-	no data

Video outputs and ports

Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.

Display Connectors	1x HDMI, 3x DisplayPort	No outputs
HDMI	+	no data

API support

APIs supported, including particular versions of those APIs.

DirectX	12 Ultimate (12_2)	N/A
Shader Model	6.6	N/A
OpenGL	4.6	N/A
OpenCL	3.0	3.0
Vulkan	1.2	N/A
CUDA	8.6	9.0

Advantages and disadvantages

---

Recency	31 May 2021	22 March 2022
Memory bus width	256	5120
Memory bandwidth	608.3	1
Pipelines / CUDA cores	6144	7296
Chip lithography	8 nm	4 nm
Thermal design power (TDP)	290 Watt	350 Watt

---

Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.

Cast your vote

Do you think we are right or mistaken in our choice? Vote by clicking "Like" button near your favorite graphics card.

---