AMD Radeon RX 6800S vs NVIDIA GeForce RTX 4070 Ti Full Specs

Summary

2,048 Shaders 2.1GHz	7,680 Shaders 2.61GHz
8GB GDDR6256GB/s	12GB GDDR6X504.2GB/s
Peak·FP32·FP16 8.6 TFLOPS	Peak·FP32·FP16 40.09 TFLOPS
Form Factor Soldered	Form Factor PCIe Card
TDP 100W	TDP 285W
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

Radeon RX 6800S17.2 TFLOPSFP16

x1

GeForce RTX 4070 Ti1.28 POPSINT4 Tensor Sparse

x74.57

Show Top Score

Theoretical Performance

Clock Speed2100MHz UC·Base·Boost·OC	Clock Speed2610MHz UC·Base·Boost·OC
Peak OPS 17.2 TFLOPSFP16	Peak OPS 1.28 POPSINT4 Tensor Sparse
-	Tensor FP8-16 320.7 TFLOPS FP8-16 Tensor Sparse 641.4 TFLOPS Tensor FP8-32 160.4 TFLOPS FP8-32 Tensor Sparse 320.7 TFLOPS
-	Tensor FP16-16 160.4 TFLOPS FP16-16 Tensor Sparse 320.7 TFLOPS Tensor FP16-32 80.18 TFLOPS FP16-32 Tensor Sparse 160.4 TFLOPS
-	BF16 40.09 TFLOPS Tensor BF16 80.18 TFLOPS BF16 Tensor Sparse 160.4 TFLOPS
Tensor TF32 -	Tensor TF32 40.09 TFLOPS
FP32 8.6 TFLOPS	FP32 40.09 TFLOPS
FP64 537.6 GFLOPS	FP64 626.4 GFLOPS
Tensor INT4 -	Tensor INT4 641.4 TOPS
-	Tensor INT8 320.7 TOPS
Ray -	Ray 92.66 TOPS
Pixel Rate 134.4 GPixel/s	Pixel Rate 208.8 GPixel/s
Texture Rate 268.8 GTexel/s	Texture Rate 626.4 GTexel/s

Core Config

Shaders 2,048 Shaders	Shaders 7,680 Shaders
TMUs 128 TMUs	TMUs 240 TMUs
ROPs 64 ROPs	ROPs 80 ROPs
Tensor Cores -	Tensor Cores 240 T-Cores
RT Cores 32 RT-Cores	RT Cores 60 RT-Cores
CUs 32 CUs	SMs 60 SMs

Clocks

Base Clock 1.8GHz	Base Clock 2.31GHz
Boost Clock 2.1GHz	Boost Clock 2.61GHz

Cache

L2 Cache 2MB shared	L2 Cache 49.1MB shared
L3 Cache 32MB shared	L3 Cache -
L3 Bandwidth 832GB/s	L3 Bandwidth -

Memory

8GB GDDR6	12GB GDDR6X
Memory Bus 128-bit	Memory Bus 192-bit
Memory Speed 16GT/s	Memory Speed 21GT/s
Memory Bandwidth 256GB/s	Memory Bandwidth 504.2GB/s
ECC No	ECC No

Power & Thermals

TDP 100W	TDP 285W
Max Temp -	Max Temp 90°C Max

Video Output

Multi-Monitor 4	Multi-Monitor 4
HDCP HDCP 2.3	HDCP HDCP 2.3

Ports

-	3x DisplayPort 1.4
-	1x HDMI 2.1

Encoder

Encoder Model VCN 3.0

Encoder Model 2x NVENC 8

Decoder

Decoder Model VCN 3.0

Decoder Model NVDEC 5

Card

Form Factor Soldered	Form Factor PCIe Card
PCIe -	PCIe 3-Slots
-	Height 137 mm (5.39") Width 304 mm (11.97") Depth 61 mm (2.4")
Cooling Passive -	Cooling Open-Air 2x Fans
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

Chip

Manufacturer AMD	Manufacturer NVIDIA
Chip Designer AMD	Chip Designer NVIDIA
Architecture RDNA 2	Architecture Ada Lovelace
Family Radeon RX 6000	Family GeForce 40
Branding	Branding
Codename Dimgrey Cavefish	Codename NV184
Chip Variant Navi 23 XL	Chip Variant AD104-250
Market Segment Desktop	Market Segment Desktop
Release Date Jan 4, 2022	Release Date Jan 5, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node N7	Fabrication Node 4N
Die Size 237mm²	Die Size 295mm²
Transistor Count 11.1 Billion	Transistor Count 35.8 Billion
Transistor Density 46.67 MTr/mm²	Transistor Density 121.6 MTr/mm²

Images

No images available

No images available

Competitors

AMDRadeon RX 6800S vs GPU NVIDIAGeForce RTX 5050 Laptop 50W AMDRadeon RX 6800S vs GPU NVIDIAGeForce RTX 5050 Laptop 80W AMDRadeon RX 6800S vs GPU NVIDIAGeForce RTX 5050 Laptop 60W Show 12 more

NVIDIAGeForce RTX 4070 Ti vs GPU AMDRadeon RX 9070 XT NVIDIAGeForce RTX 4070 Ti vs GPU NVIDIAGeForce RTX 5070 NVIDIAGeForce RTX 4070 Ti vs GPU NVIDIAGeForce RTX 5070 Ti Show 12 more