NVIDIA GeForce RTX 4070 Super vs NVIDIA L4 Full Specs - HMC

7,168 Shaders 2.48GHz	7,680 Shaders 2.04GHz
12GB GDDR6X504.2GB/s	24GB GDDR6300.1GB/s
·· 35.48 TFLOPS	·· 31.33 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 225W	TDP 72W
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors 1x 16-Pin 12VHPWR

GeForce RTX 4070 Super

GeForce RTX 4070 Super1.14 POPSINT4 Tensor Sparse

x1.13

L41 POPSINT4 Tensor Sparse

x1

Clock Speed ···	Clock Speed ···
Peak OPS 1.14 POPSINT4 Tensor Sparse	Peak OPS 1 POPSINT4 Tensor Sparse
Tensor FP8-16 283.9 TFLOPS FP8-16 Tensor Sparse 567.7 TFLOPS Tensor FP8-32 141.9 TFLOPS FP8-32 Tensor Sparse 283.9 TFLOPS	Tensor FP8-16 250.7 TFLOPS FP8-16 Tensor Sparse 501.4 TFLOPS Tensor FP8-32 125.3 TFLOPS FP8-32 Tensor Sparse 250.7 TFLOPS
Tensor FP16-16 141.9 TFLOPS FP16-16 Tensor Sparse 283.9 TFLOPS Tensor FP16-32 70.96 TFLOPS FP16-32 Tensor Sparse 141.9 TFLOPS	Tensor FP16-16 125.3 TFLOPS FP16-16 Tensor Sparse 250.7 TFLOPS Tensor FP16-32 62.67 TFLOPS FP16-32 Tensor Sparse 125.3 TFLOPS
BF16 35.48 TFLOPS Tensor BF16 70.96 TFLOPS BF16 Tensor Sparse 141.9 TFLOPS	BF16 31.33 TFLOPS Tensor BF16 62.67 TFLOPS BF16 Tensor Sparse 125.3 TFLOPS
Tensor TF32 35.48 TFLOPS	Tensor TF32 31.33 TFLOPS
FP32 35.48 TFLOPS	FP32 31.33 TFLOPS
FP64 554.4 GFLOPS	FP64 489.6 GFLOPS
Tensor INT4 567.7 TOPS	Tensor INT4 501.4 TOPS
Tensor INT8 283.9 TOPS	Tensor INT8 250.7 TOPS
Ray 82.01 TOPS	Ray 72.43 TOPS
Pixel Rate 198 GPixel/s	Pixel Rate 163.2 GPixel/s
Texture Rate 554.4 GTexel/s	Texture Rate 489.6 GTexel/s

Shaders 7,168 Shaders	Shaders 7,680 Shaders
TMUs 224 TMUs	TMUs 240 TMUs
ROPs 80 ROPs	ROPs 80 ROPs
Tensor Cores 224 T-Cores	Tensor Cores 240 T-Cores
RT Cores 56 RT-Cores	RT Cores 60 RT-Cores
SMs 56 SMs	SMs 60 SMs

Base Clock 1.98GHz	Base Clock 795MHz
Boost Clock 2.48GHz	Boost Clock 2.04GHz

L1 64KB/SM Tex	L1 64KB/SM Tex
L2 Cache 36MB shared	L2 Cache 48MB shared

12GB GDDR6X	24GB GDDR6
Memory Bus 192-bit	Memory Bus 192-bit
Memory Speed 21GT/s	Memory Speed 12.5GT/s
Memory Bandwidth 504.2GB/s	Memory Bandwidth 300.1GB/s
ECC No	ECC No

TDP

225W

TDP

72W

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

3x DisplayPort 1.4

1x HDMI 2.1

-

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

Encoder 2x NVENC 8	Encoder 2x NVENC 8
Codec AVC (H.264) HEVC (H.265) AV1	Codec AVC (H.264) HEVC (H.265) AV1

Decoder NVDEC 5	Decoder NVDEC 5
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) AV1

Form Factor PCIe Card	Form Factor PCIe Card
PCIe PCIe 4.0 x16 2.1-Slots	PCIe PCIe 4.0 x16 1-Slots
Height 112mm (4.41") Width 267mm (10.51") Depth 42mm (1.65")	Height 56mm (2.21") Width 169mm (6.65") Depth 20mm (0.79")
Cooling Open-Air 2x Fans	Cooling Passive -
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors 1x 16-Pin 12VHPWR

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ada Lovelace	Architecture Ada Lovelace
Family GeForce 40	Family Server
Branding	Branding
Codename NV184	Codename NV184
Chip Variant AD104-250	Chip Variant AD104-250
Market Segment Desktop	Market Segment Server
Release Date Jan 8, 2024	Release Date Mar 21, 2023

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