NVIDIA GeForce RTX 4070 vs Qualcomm Adreno 642 Full Specs

Summary

5,888 Shaders 2.48GHz	768 Shaders 550MHz
12GB GDDR6X504.2GB/s placeholder	Shared Memory25.6GB/s LPDDR5·LPDDR4X
Peak·FP32·FP16 29.15 TFLOPS	Peak·FP32·FP16 844.8 GFLOPS
Form Factor PCIe Card	Form Factor iGPU
TDP 200W	TDP 5W
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors -

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

x552.00

Adreno 6421.69 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed2475MHz UC·Base·Boost·OC	Clock Speed550MHz UC·Base·Boost·OC
Peak OPS 932.7 TOPSINT4 Tensor Sparse	Peak OPS 1.69 TFLOPSFP16
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 FP16-16 116.6 TFLOPS FP16-16 Tensor Sparse 233.2 TFLOPS Tensor FP16-32 58.29 TFLOPS FP16-32 Tensor Sparse 116.6 TFLOPS	-
BF16 29.15 TFLOPS Tensor BF16 58.29 TFLOPS BF16 Tensor Sparse 116.6 TFLOPS	-
Tensor TF32 29.15 TFLOPS	Tensor TF32 -
FP32 29.15 TFLOPS	FP32 844.8 GFLOPS
FP64 455.4 GFLOPS	FP64 211.2 GFLOPS
Tensor INT4 466.3 TOPS	Tensor INT4 -
Tensor INT8 233.2 TOPS	-
Ray 67.37 TOPS	Ray -
Pixel Rate 158.4 GPixel/s	Pixel Rate 13.2 GPixel/s
Texture Rate 455.4 GTexel/s	Texture Rate 26.4 GTexel/s

Core Config

Shaders 5,888 Shaders	Shaders 768 Shaders
TMUs 184 TMUs	TMUs 48 TMUs
ROPs 64 ROPs	ROPs 24 ROPs
Tensor Cores 184 T-Cores	Tensor Cores -
RT Cores 46 RT-Cores	RT Cores -
SMs 46 SMs	EUs 6 EUs

Clocks

Base Clock 1.92GHz	Base Clock 490MHz
Boost Clock 2.48GHz	Boost Clock 550MHz

Cache

L1 64KB/SM Tex	L1 8KB/CU
L2 Cache 36MB shared	L2 Cache 128KB shared
L3 Cache -	L3 Cache 2MB shared

Memory

12GB GDDR6X placeholder	Shared Memory LPDDR5·LPDDR4X
Memory Bus 192-bit	Memory Bus 32-bit
Memory Speed 21GT/s	Memory Speed 6.4GT/s
Memory Bandwidth 504.2GB/s	Memory Bandwidth 25.6GB/s
ECC No	ECC No

Power & Thermals

TDP 200W

TDP 5W

Video Output

Max Resolution 7680x4320	Max Resolution 2520x1080
Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 60Hz	Refresh Rate Calculator 1920x1080 Resolution1080p FHD Refresh Rate 78Hz
Multi-Monitor 4	Multi-Monitor 1
Adaptive Sync G-Sync FreeSync	Adaptive Sync -
DSC Supported	DSC Not Supported
HDCP HDCP 2.3	HDCP -

Ports

3x DisplayPort 1.4 1x HDMI 2.1

-

API Support

Shader Model 6.7	Shader Model -
DirectX DirectX 12 Direct3D 12_3	DirectX DirectX 12 Direct3D 12_1
OpenGL 4.6 OpenCL 3 Vulkan 1.3	OpenGL 3.2 OpenCL 2 Vulkan 1.1
CUDA 8.9 PureVideo HD VP12 VDPAU Feature Set L	-

Encoder

Encoder 2x NVENC 8	Encoder Hexagon 770
Codec - - - - - AVC (H.264) HEVC (H.265) AV1	Codec H.263 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) -

Decoder

Decoder NVDEC 5	Decoder Hexagon 770
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 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) -

Card

Form Factor PCIe Card	Form Factor iGPU
PCIe PCIe 4.0 x16 2.1-Slots	PCIe -
Height 112mm (4.41") Width 244mm (9.61") Depth 42mm (1.65")	-
Cooling Open-Air 2x Fans	Cooling Open-Air -
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors -

Chip

Manufacturer NVIDIA	Manufacturer Qualcomm
Chip Designer NVIDIA	Chip Designer Qualcomm
Architecture Ada Lovelace	Architecture Adreno 600
Family GeForce 40	Family Adreno 600
Branding	Branding
Codename NV184	Codename -
Chip Variant AD104-250	Chip Variant -
Market Segment Desktop	Market Segment Smartphone
Release Date Apr 13, 2023	Release Date May 20, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4N	Fabrication Node N6
Die Size 295mm²	Die Size -
Transistor Count 35.8B	Transistor Count -
Transistor Density 121.6 MTr/mm²	Transistor Density -

Images