NVIDIA GeForce RTX 4070 vs AMD Radeon RX 9070 Full Specs

Summary

5,888 Shaders 2.48GHz	3,584 Shaders 2.52GHz
12GB GDDR6X504.2GB/s	16GB GDDR6640GB/s
Peak·FP32·FP16 29.15 TFLOPS	Peak·FP32·FP16 36.13 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 200W	TDP 220W
Power Connectors 1x 16-Pin 12VHPWR -	Power Connectors - 2x 8-Pin

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 4070932.7 TOPSINT4 Tensor Sparse

x1

Radeon RX 90701.16 POPSINT4 Tensor Sparse

x1.24

Show Top Score

Theoretical Performance

Clock Speed2475MHz UC·Base·Boost·OC	Clock Speed2520MHz UC·Base·Boost·OC
Peak OPS 932.7 TOPSINT4 Tensor Sparse	Peak OPS 1.16 POPSINT4 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 FP8-16 144.5 TFLOPS FP8-16 Tensor Sparse 289 TFLOPS Tensor FP8-32 144.5 TFLOPS FP8-32 Tensor Sparse 289 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	Tensor FP16-16 72.25 TFLOPS FP16-16 Tensor Sparse 144.5 TFLOPS Tensor FP16-32 72.25 TFLOPS FP16-32 Tensor Sparse 144.5 TFLOPS
BF16 29.15 TFLOPS Tensor BF16 58.29 TFLOPS BF16 Tensor Sparse 116.6 TFLOPS	BF16 72.25 TFLOPS Tensor BF16 72.25 TFLOPS BF16 Tensor Sparse 144.5 TFLOPS
Tensor TF32 29.15 TFLOPS	Tensor TF32 -
FP32 29.15 TFLOPS	FP32 36.13 TFLOPS
FP64 455.4 GFLOPS	FP64 1.13 TFLOPS
Tensor INT4 466.3 TOPS	Tensor INT4 578 TOPS
Tensor INT8 233.2 TOPS	Tensor INT8 289 TOPS
Ray 67.37 TOPS	Ray -
Pixel Rate 158.4 GPixel/s	Pixel Rate 322.6 GPixel/s
Texture Rate 455.4 GTexel/s	Texture Rate 564.5 GTexel/s

Core Config

Shaders 5,888 Shaders	Shaders 3,584 Shaders
TMUs 184 TMUs	TMUs 224 TMUs
ROPs 64 ROPs	ROPs 128 ROPs
Tensor Cores 184 T-Cores	Tensor Cores 112 T-Cores
RT Cores 46 RT-Cores	RT Cores 56 RT-Cores
SMs 46 SMs	CUs 56 CUs

Clocks

Base Clock 1.92GHz	Base Clock 2.21GHz
Boost Clock 2.48GHz	Boost Clock 2.52GHz

Cache

L0 Cache -	L0 Cache 64KB/WGP
L1 64KB/SM Tex	L1 256KB/Array
L2 Cache 36MB shared	L2 Cache 8MB shared
L3 Cache -	L3 Cache 64MB shared
L3 Bandwidth -	L3 Bandwidth 2.25TB/s

Memory

12GB GDDR6X	16GB GDDR6
Memory Bus 192-bit	Memory Bus 256-bit
Memory Speed 21GT/s	Memory Speed 20GT/s
Memory Bandwidth 504.2GB/s	Memory Bandwidth 640GB/s
ECC No	ECC No

Power & Thermals

TDP 200W

TDP 220W

Video Output

Max Resolution 7680x4320	Max Resolution 7680x4320
Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 60Hz	Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 165Hz
Multi-Monitor 4	Multi-Monitor 3
Adaptive Sync G-Sync FreeSync	Adaptive Sync - FreeSync
DSC Supported	DSC Supported
HDCP HDCP 2.3	HDCP HDCP 2.3

Ports

3x DisplayPort 1.4 1x HDMI 2.1

3x DisplayPort 2.1 1x HDMI 2.1

API Support

Shader Model 6.7	Shader Model 6.8
DirectX DirectX 12 Direct3D 12_3	DirectX DirectX 12 Direct3D 12_2
OpenGL 4.6 OpenCL 3 Vulkan 1.3	OpenGL 4.6 OpenCL 2.2 Vulkan 1.3
CUDA 8.9 GFX - PureVideo HD VP12 VDPAU Feature Set L	CUDA - GFX 12 PureVideo HD - VDPAU -

Encoder

Encoder 2x NVENC 8	Encoder VCN 4.0
Codec - AVC (H.264) HEVC (H.265) AV1	Codec VP9 AVC (H.264) HEVC (H.265) AV1

Decoder

Decoder NVDEC 5	Decoder VCN 4.0
Codec MPEG-1 MPEG-2 MPEG-4 - VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1	Codec MPEG-1 MPEG-2 MPEG-4 JPEG VC-1 - VP9 AVC (H.264) HEVC (H.265) AV1

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe PCIe 4.0 x16 2.1-Slots	PCIe PCIe 5.0 x16 2.5-Slots
Height 112mm (4.41") Width 244mm (9.61") Depth 42mm (1.65")	Height 111mm (4.37") Width 267mm (10.51") Depth 50mm (1.97")
Cooling Open-Air 2x Fans	Cooling Open-Air 3x Fans
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors 2x 8-Pin
Multi-GPU -	Multi-GPU Multi-GPU Support Supported Multi-GPU Type CrossFire XDMA

Chip

Manufacturer NVIDIA	Manufacturer AMD
Chip Designer NVIDIA	Chip Designer AMD
Architecture Ada Lovelace	Architecture RDNA 4
Family GeForce 40	Family Radeon RX 9000
Branding	Branding
Codename NV184	Codename -
Chip Variant AD104-250	Chip Variant Navi 48 XL
Market Segment Desktop	Market Segment Desktop
Release Date Apr 13, 2023	Release Date Jan 6, 2025

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4N	Fabrication Node N4P
Die Size 295mm²	Die Size 357mm²
Transistor Count 35.8B	Transistor Count 53.9B
Transistor Density 121.6 MTr/mm²	Transistor Density 151.2 MTr/mm²

Images

Competitors

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

AMDRadeon RX 9070 vs NVIDIAGeForce RTX 4070 AMDRadeon RX 9070 vs GPU NVIDIAGeForce RTX 5070 AMDRadeon RX 9070 vs GPU PowerColorRadeon RX 6800 Red Dragon Show 12 more