GPUs

NVIDIA GeForce RTX 4080 Max-Q vs NVIDIA GeForce RTX 5070 Laptop 60W Full Specs

7,424 Shaders
1.35GHz
4,608 Shaders
1.85GHz
12GB GDDR6432GB/s
8GB GDDR7448GB/s
··
20.04 TFLOPS
··
17.02 TFLOPS
Form Factor
Soldered
Form Factor
Soldered
TDP
60W
TDP
60W

GeForce RTX 4080 Max-QGeForce RTX 4080 Max-Q641.4 TOPSINT4 Tensor Sparse
x1
GeForce RTX 5070 Laptop 60WGeForce RTX 5070 Laptop 60W709.3 TFLOPSFP4 Tensor Sparse
x1.11

Clock Speed
···
Clock Speed
···
Peak OPS
641.4 TOPSINT4 Tensor Sparse
Peak OPS
709.3 TFLOPSFP4 Tensor Sparse
-
Tensor FP4
354.6 TFLOPS
FP4 Tensor Sparse
709.3 TFLOPS
Tensor FP8-16
160.4 TFLOPS
FP8-16 Tensor Sparse
320.7 TFLOPS
Tensor FP8-32
80.18 TFLOPS
FP8-32 Tensor Sparse
160.4 TFLOPS
Tensor FP8-16
177.3 TFLOPS
FP8-16 Tensor Sparse
354.6 TFLOPS
Tensor FP8-32
88.66 TFLOPS
FP8-32 Tensor Sparse
177.3 TFLOPS
Tensor FP16-16
80.18 TFLOPS
FP16-16 Tensor Sparse
160.4 TFLOPS
Tensor FP16-32
40.09 TFLOPS
FP16-32 Tensor Sparse
80.18 TFLOPS
Tensor FP16-16
88.66 TFLOPS
FP16-16 Tensor Sparse
177.3 TFLOPS
Tensor FP16-32
44.33 TFLOPS
FP16-32 Tensor Sparse
88.66 TFLOPS
BF16
20.04 TFLOPS
Tensor BF16
40.09 TFLOPS
BF16 Tensor Sparse
80.18 TFLOPS
BF16
17.02 TFLOPS
Tensor BF16
44.33 TFLOPS
BF16 Tensor Sparse
88.66 TFLOPS
Tensor TF32
20.04 TFLOPS
Tensor TF32
22.16 TFLOPS
FP32
20.04 TFLOPS
FP32
17.02 TFLOPS
FP64
313.2 GFLOPS
FP64
266 GFLOPS
Tensor INT4
320.7 TOPS
Tensor INT4
-
Tensor INT8
160.4 TOPS
Tensor INT8
177.3 TOPS
Ray
46.33 TOPS
Ray
51.62 TOPS
Pixel Rate
108 GPixel/s
Pixel Rate
88.7 GPixel/s
Texture Rate
313.2 GTexel/s
Texture Rate
266 GTexel/s

Shaders
7,424 Shaders
Shaders
4,608 Shaders
TMUs
232 TMUs
TMUs
144 TMUs
ROPs
80 ROPs
ROPs
48 ROPs
Tensor Cores
232 T-Cores
Tensor Cores
144 T-Cores
RT Cores
58 RT-Cores
RT Cores
36 RT-Cores
SMs
58 SMs
SMs
36 SMs

Base Clock
795MHz
Base Clock
1.56GHz
Boost Clock
1.35GHz
Boost Clock
1.85GHz
Tensor Clock
-
Tensor Clock
2.4GHz

L2 Cache
49.1MB shared
L2 Cache
32.8MB shared

12GB GDDR6
8GB GDDR7
Memory Bus
192-bit
Memory Bus
128-bit
Memory Speed
18GT/s
Memory Speed
28GT/s
Memory Bandwidth
432GB/s
Memory Bandwidth
448GB/s

TDP
60W
TDP
60W

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

Encoder Model
2x NVENC 8
Encoder Model
NVENC 9

Decoder Model
NVDEC 5
Decoder Model
NVDEC 6

Form Factor
Soldered
Form Factor
Soldered

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
GeForce RTX 2022 branding
Branding
GeForce RTX 2022 branding
Codename
NV184
Codename
NV196
Chip Variant
AD104-250
Chip Variant
-
Market Segment
Laptop
Market Segment
Laptop
Release Date
Feb 8, 2023
Release Date
Jan 6, 2025

Foundry
TSMC
Foundry
TSMC
Fabrication Node
4N
Fabrication Node
4NP
Die Size
295mm²
Die Size
183mm²
Transistor Count
35.8 Billion
Transistor Count
23 Billion
Transistor Density
121.6 MTr/mm²
Transistor Density
125.7 MTr/mm²

No images available
No images available