Qualcomm Snapdragon 820 vs Google Tensor G2
SOC Specs Compare
CPU
Architecture
2x 2.15 GHz – Kryo2x 1.593 GHz – Kryo
2x 2.85 GHz – Cortex-X12x 2.35 GHz – Cortex-A784x 1.8 GHz – Cortex-A55
Frequency
2150 MHz
2850 MHz
Cores
4
8
Instruction set
ARMv8-A
ARMv8.4-A
L1 cache
64 KB
-
L2 cache
0
-
Process
14 nm
5 nm
Transistor count
2
-
TDP
11 W
7 W
Manufacturing
TSMC
Samsung
L3 cache
-
0
Graphics
GPU name
Adreno 530
Mali-G710 MP7
GPU frequency
624 MHz
850 MHz
Execution units
1
7
Shading units
256
96
Vulkan version
1.0
1.3
OpenCL version
2.0
2.0
DirectX version
11
-
Memory
Memory Type
LPDDR4
LPDDR5
Memory frequency
1866 MHz
3200 MHz
Bus
2x 32 Bit
4x 16 Bit
Max bandwidth
29.8 Gbit/s
51.2 Gbit/s
Multimedia (ISP)
Neural processor (NPU)
Hexagon 680
Next-gen Tensor Processing Unit
Storage type
eMMC 5.1, UFS 2.0
UFS 3.1
Max display resolution
3840 x 2160
3840 x 2160
Max camera resolution
1x 28MP, 2x 13MP
1x 200MP, 2x 32MP
Video capture
4K at 30FPS
4K at 60FPS
Video playback
4K at 30FPS
4K at 60FPS
Video codecs
H.264, H.265
H.264, H.265, AV1, VP9
Audio codecs
AIFF, CAF, MP3, MP4, WAV
AAC, AIFF, CAF, MP3, MP4, WAV
Connectivity
4G support
LTE Cat. 12
LTE Cat. 24
5G support
No
Yes
Download speed
Up to 600 Mbps
Up to 7350 Mbps
Upload speed
Up to 150 Mbps
Up to 3670 Mbps
Wi-Fi
5
6
Bluetooth
4.1
5.2
Navigation
GPS, GLONASS, Beidou, Galileo, QZSS, SBAS
GPS, GLONASS, Beidou, Galileo, QZSS, NAVIC
Info
AI
NPU
-
Next-gen Tensor Processing Unit
📊 Benchmark
AnTuTu 10
260,148
907,387
Geekbench 6
323
1,439
Geekbench 6
827
3,802
FP32 (float)
319
1,142