EVGA GeForce RTX 3070 XC3 Ultra vs NVIDIA GeForce RTX 4070 Full Specs

Summary

5,888 Shaders 1.77GHz	5,888 Shaders 2.48GHz
8GB GDDR6448GB/s	12GB GDDR6X504.2GB/s
Peak·FP32·FP16 20.84 TFLOPS	Peak·FP32·FP16 29.15 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 220W	TDP 200W
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

GeForce RTX 3070 XC3 Ultra667 TOPSINT4 Tensor Sparse

x1

GeForce RTX 4070932.7 TOPSINT4 Tensor Sparse

x1.40

Show Top Score

Theoretical Performance

Clock Speed1770MHz UC·Base·Boost·OC	Clock Speed2475MHz UC·Base·Boost·OC
Peak OPS 667 TOPSINT4 Tensor Sparse	Peak OPS 932.7 TOPSINT4 Tensor Sparse
-	Tensor FP8-16 233.2 TFLOPS FP8-16 Tensor Sparse 466.3 TFLOPS Tensor FP8-32 116.6 TFLOPS FP8-32 Tensor Sparse 233.2 TFLOPS
Tensor FP16-16 83.37 TFLOPS FP16-16 Tensor Sparse 166.7 TFLOPS Tensor FP16-32 41.69 TFLOPS FP16-32 Tensor Sparse 83.37 TFLOPS	Tensor FP16-16 116.6 TFLOPS FP16-16 Tensor Sparse 233.2 TFLOPS Tensor FP16-32 58.29 TFLOPS FP16-32 Tensor Sparse 116.6 TFLOPS
BF16 20.84 TFLOPS Tensor BF16 41.69 TFLOPS BF16 Tensor Sparse 83.37 TFLOPS	BF16 29.15 TFLOPS Tensor BF16 58.29 TFLOPS BF16 Tensor Sparse 116.6 TFLOPS
Tensor TF32 20.84 TFLOPS	Tensor TF32 29.15 TFLOPS
FP32 20.84 TFLOPS	FP32 29.15 TFLOPS
FP64 325.7 GFLOPS	FP64 455.4 GFLOPS
Tensor INT4 333.5 TOPS	Tensor INT4 466.3 TOPS
Tensor INT8 166.7 TOPS	Tensor INT8 233.2 TOPS
Ray 31.44 TOPS	Ray 67.37 TOPS
Pixel Rate 169.9 GPixel/s	Pixel Rate 158.4 GPixel/s
Texture Rate 325.7 GTexel/s	Texture Rate 455.4 GTexel/s

Core Config

Shaders 5,888 Shaders	Shaders 5,888 Shaders
TMUs 184 TMUs	TMUs 184 TMUs
ROPs 96 ROPs	ROPs 64 ROPs
Tensor Cores 184 T-Cores	Tensor Cores 184 T-Cores
RT Cores 46 RT-Cores	RT Cores 46 RT-Cores
SMs 46 SMs	SMs 46 SMs

Clocks

Base Clock 1.5GHz	Base Clock 1.92GHz
Boost Clock 1.77GHz	Boost Clock 2.48GHz

Cache

L2 Cache 4.1MB shared

L2 Cache 36.9MB shared

Memory

8GB GDDR6	12GB GDDR6X
Memory Bus 256-bit	Memory Bus 192-bit
Memory Speed 14GT/s	Memory Speed 21GT/s
Memory Bandwidth 448GB/s	Memory Bandwidth 504.2GB/s
ECC No	ECC No

Power & Thermals

TDP 220W	TDP 200W
Max Temp 93°C Max	Max Temp -

Video Output

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

Ports

3x DisplayPort 1.4	3x DisplayPort 1.4
1x HDMI 2.1	1x HDMI 2.1

Encoder

Encoder Model NVENC 7

Encoder Model 2x NVENC 8

Decoder

Decoder Model NVDEC 5

Decoder Model NVDEC 5

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 2.1-Slots	PCIe 2.1-Slots
Height 111.2 mm (4.38") Width 285.4 mm (11.24") Depth 43 mm (1.69")	Height 112 mm (4.41") Width 244 mm (9.61") Depth 42 mm (1.65")
Cooling Open-Air 3x Fans	Cooling Open-Air 2x Fans
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

Chip

Manufacturer EVGA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ampere	Architecture Ada Lovelace
Family GeForce 30	Family GeForce 40
Branding	Branding
Codename NV174	Codename NV184
Chip Variant GA104-150-A1	Chip Variant AD104-250
Market Segment Desktop	Market Segment Desktop
Release Date Oct 29, 2020	Release Date Apr 13, 2023

Fabrication

Foundry Samsung	Foundry TSMC
Fabrication Node 8N	Fabrication Node 4N
Die Size 393mm²	Die Size 295mm²
Transistor Count 17.4 Billion	Transistor Count 35.8 Billion
Transistor Density 44.33 MTr/mm²	Transistor Density 121.6 MTr/mm²

Images

No images available

No images available

Competitors

EVGAGeForce RTX 3070 XC3 Ultra vs GPU NVIDIAGeForce RTX 4060 Ti EVGAGeForce RTX 3070 XC3 Ultra vs GPU NVIDIAGeForce RTX 5070 EVGAGeForce RTX 3070 XC3 Ultra vs GPU NVIDIAGeForce RTX 4070 Super Show 12 more

NVIDIAGeForce RTX 4070 vs GPU AMDRadeon RX 9070 NVIDIAGeForce RTX 4070 vs GPU AMDRadeon RX 7700 NVIDIAGeForce RTX 4070 vs GPU AMDRadeon RX 7700 XT Show 12 more