Performance Benchmarks

This page provides a centralized reference for evaluating AI inference performance across MediaTek Genio platforms, which aggregates benchmarking results for various AI workloads, including analytical AI and generative AI, across multiple inference frameworks such as TFLite (LiteRT) and ONNX Runtime.

Important

For more platform-specific details and comprehensive performance data, please refer to the Model Zoo.

AI Supporting Scope

The following table summarizes the AI capabilities and framework support across different MediaTek Genio platforms.

AI Supporting Scope Across Different Platform

Platform	OS	TFLite - Analytical AI (Online)	TFLite - Analytical AI (Offline)	TFLite - Generative AI	ONNX Runtime - Analytical AI
Genio 360/360P	Android	CPU + GPU + NPU	NPU	NPU	CPU + NPU
	Yocto	CPU + GPU + NPU	NPU	NPU	CPU + NPU
Genio 420/520/720	Android	CPU + GPU + NPU	NPU	NPU	CPU + NPU
	Yocto	CPU + GPU + NPU	NPU	NPU	CPU + NPU
Genio 510/700	Android	CPU + GPU + NPU	NPU	X	X
	Yocto	CPU + GPU + NPU	NPU	X	CPU
	Ubuntu	CPU + GPU + NPU	NPU	X	X
Genio 1200	Android	CPU + GPU + NPU	NPU	X	X
	Yocto	CPU + GPU + NPU	NPU	X	CPU
	Ubuntu	CPU + GPU + NPU	NPU	X	X
Genio 350	Android	CPU + GPU + NPU	X	X	X
	Yocto	CPU + GPU	X	X	CPU
	Ubuntu	CPU + GPU	X	X	X
MT8875	Android	CPU + GPU + NPU	NPU	NPU	CPU + NPU
MT8883	Android	CPU + GPU + NPU	NPU	NPU	CPU + NPU
MT8893	Android	CPU + GPU + NPU	NPU	NPU	CPU + NPU

TFLite(LiteRT) - Analytical AI

The following tables list the validated TFLite analytical models and their performance across Genio platforms. The statistics were measured using offline inference with performance mode enabled.

Important

Genio 350 does not include an NPU (MDLA/APU). Values shown for Genio 350 are measured on the GPU delegate (not NeuronSDK). For all other Genio and MTK platforms, the shown numbers use NeuronSDK / Neuronrt-MDLA (offline NPU inference).

Models for Detection

Genio 350

Genio 360

Genio 420

Genio 510

Genio 520

Genio 700

Genio 720

Genio 1200

MT8875

MT8883

MT8893

Task

Model Name

Source model type

Data Type

Input Size

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Detail

Object Detection

YOLOv5s [1]

.pt

Quant8

640x640

X

8.68

5.98

16.00

6.02

10.10

5.35

19.00

–

–

3.42

Link

Object Detection

YOLOv5s [1]

.pt

Float32

640x640

X

28.25

20.15

44.90

18.49

32.30

16.66

37.00

–

–

14.40

Link

Object Detection

YOLOv8s [1]

.pt

Quant8

640x640

X

12.92

9.40

24.00

9.02

17.00

8.04

28.40

–

–

5.64

Link

Object Detection

YOLOv8s [1]

.pt

Float32

640x640

X

42.41

30.77

69.30

26.83

50.30

24.41

54.60

–

–

16.34

Link

Footnotes

[1] (1,2,3,4)

AGPL-3.0 License: YOLOv5s and YOLOv8s are licensed under AGPL-3.0 by Ultralytics. Pre-converted models are not directly provided due to copyleft license restrictions. See YOLOv5s and YOLOv8s for details.

Models for Classification

					Genio 350	Genio 360	Genio 420	Genio 510	Genio 520	Genio 700	Genio 720	Genio 1200	MT8875	MT8883	MT8893
Task	Model Name	Source model type	Data Type	Input Size	Inference Time (ms)	Inference Time (ms)	Inference Time (ms)	Inference Time (ms)	Inference Time (ms)	Inference Time (ms)	Inference Time (ms)	Inference Time (ms)	Inference Time (ms)	Inference Time (ms)	Inference Time (ms)	Detail
Classification	DenseNet	.pt	Quant8	224x224	212.44	5.86	4.27	7.30	4.17	5.30	3.83	6.00	–	–	2.40	Link
Classification	DenseNet	.pt	Float32	224x224	205.45	12.07	8.76	16.30	8.84	11.30	7.72	12.40	–	–	4.47	Link
Classification	EfficientNet	.pt	Quant8	224x224	52.28	2.20	1.46	4.00	1.59	3.00	1.56	3.00	–	–	1.16	Link
Classification	EfficientNet	.pt	Float32	224x224	44.24	4.85	3.39	9.30	3.30	6.00	3.15	6.10	–	–	2.21	Link
Classification	MobileNetV2	.pt	Quant8	224x224	29.38	1.28	0.80	1.00	0.90	1.00	0.97	1.00	–	–	0.78	Link
Classification	MobileNetV2	.pt	Float32	224x224	25.85	2.60	1.64	3.00	1.78	2.00	1.71	2.10	–	–	1.29	Link
Classification	MobileNetV3	.pt	Quant8	224x224	11.56	0.91	0.64	1.00	0.59	0.40	0.74	0.90	–	–	0.64	Link
Classification	MobileNetV3	.pt	Float32	224x224	10.12	1.67	1.09	2.00	1.13	1.10	1.20	2.00	–	–	0.97	Link
Classification	ResNet	.pt	Quant8	224x224	96.02	2.25	1.52	2.00	1.46	2.00	1.48	2.10	–	–	1.08	Link
Classification	ResNet	.pt	Float32	224x224	94.41	6.20	4.51	9.30	4.04	6.30	3.86	8.40	–	–	2.56	Link
Classification	SqueezeNet	.pt	Quant8	224x224	58.02	1.55	1.11	1.00	0.99	1.00	1.11	1.00	–	–	0.86	Link
Classification	SqueezeNet	.pt	Float32	224x224	56.68	3.57	2.54	4.10	2.26	3.00	2.31	3.00	–	–	1.64	Link
Classification	VGG	.pt	Quant8	224x224	434.96	17.72	12.78	X	13.32	X	11.17	24.40	–	–	6.47	Link
Classification	VGG	.pt	Float32	224x224	427.86	69.25	40.39	80.30	38.24	56.30	33.17	50.40	–	–	19.87	Link

Models for Recognition

Genio 350

Genio 360

Genio 420

Genio 510

Genio 520

Genio 700

Genio 720

Genio 1200

MT8875

MT8883

MT8893

Task

Model Name

Source model type

Data Type

Input Size

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Inference Time (ms)

Detail

Recognition

VGGFace

.pt

Quant8

224x224

X

18.21

13.07

X

13.71

X

11.50

24.40

–

–

6.58

Link

Recognition

VGGFace

.pt

Float32

224x224

430.31

71.01

40.98

81.30

39.13

56.30

33.80

49.50

–

–

20.00

Link

Community-Contributed Model

Model Name	Source model type	Data Type	Input Size	Genio 360	Genio 420	Genio 520	Gneio 720	Genio 510	Genio 700	Genio 1200
MobileNetV1	.tflite	Quant8	224x224	X	0.85	0.93	0.92	1.28	1.04	1.05
YOLOv11s-quant8	.tflite	Quant8	640x640	11.39	18.85	18.62	8.52	27.04	19.04	X

TFLite(LiteRT) - Generative AI

For Generative AI workloads, the following tables provide representative performance data for reference and platform capability validation.

Note

The following symbols are used in the performance tables below:

• -- : To be released.

• Q3/E : Support planned for Q3 (estimated).

• V : Supported and verified on this platform.

• X : Platform does not support this model.

Unless otherwise noted, all models listed below are supported on both Android and Yocto OS. Models or sections explicitly marked Android-only are not available on Yocto.

LLM Performance Comparison

Performance Comparison (Prompt Mode / Generative Mode) (Unit: tok/s)

Model	Genio 360	Genio 420	Genio 520	Genio 720	GenioPro 5100	MT8875	MT8883	MT8893
Qwen3-0.6B	318.66 / 14.22	420.38 / 21.44	526.43 / 23.04	535.94 / 22.93	Q4/E	750.47 / 29.48	1166.64 / 55.20	Q3/E
Qwen3-1.7B	152.67 / 8.69	222.83 / 13.03	258.83 / 13.72	262.73 / 13.84	Q4/E	238.31 / 6.63	562.80 / 30.30	1160.31 / 36.47
Qwen3-4B	73.21 / 3.53	105.18 / 6.87	126.12 / 7.30	125.58 / 7.25	Q4/E	173.79 / 6.84	267.14 / 15.81	Q3/E
Qwen3-8B	X	65.04 / 4.58	79.95 / 4.77	80.17 / 4.76	536.44 / 8.44	88.49 / 3.97	121.11 / 8.08	Q3/E
Qwen2.5-1.5B-Instruct	199.70 / 12.21	294.22 / 17.89	340.29 / 18.99	337.06 / 19.25	By Request	394.42 / 17.20	814.12 / 38.05	1621.85 / 38.57
Qwen2.5-3B-Instruct	94.62 / 6.71	132.30 / 9.98	161.19 / 10.38	163.23 / 10.64	By Request	220.04 / 9.55	414.49 / 20.91	751.06 / 20.87
Qwen2.5-7B-Instruct	X	57.79 / 4.61	69.71 / 4.86	69.47 / 4.73	By Request	80.92 / 4.36	196.22 / 9.07	471.95 / 11.74
gemma3-1B (Text Only)	359.43 / 16.58	513.69 / 24.58	598.27 / 27.23	583.01 / 26.44	Q4/E	–	1306.25 / 34.55	Q3/E
gemma3-4B (Text-Only)	92.76 / 3.44	149.00 / 5.69	176.90 / 5.90	176.79 / 5.93	Q4/E	199.32 / 6.14	404.31 / 13.53	Q3/E
llama3.2-1B-Instruct	233.97 / 15.94	329.32 / 21.58	385.77 / 24.76	400.57 / 24.92	Q4/E	514.98 / 23.17	804.68 / 36.88	2093.61 / 61.14
llama3.2-3B-Instruct	X	120.17 / 9.92	153.84 / 10.26	153.56 / 10.36	Q4/E	202.58 / 9.29	351.83 / 16.48	1022.95 / 25.05
Phi-3-mini-4k-instruct	74.79 / 4.45	101.94 / 6.30	126.82 / 7.26	127.56 / 7.28	Q4/E	Q4/E	Q4/E	828.87 / 18.87
Phi-3.5-mini-instruct	77.82 / 3.27	111.01 / 5.30	136.84 / 6.09	136.63 / 6.29	Q4/E	Q4/E	Q4/E	Q4/E

VLM Performance Comparison

Performance Comparison (ViT Inference Time (s) / Prompt (tok/s) / Generative (tok/s))

Model	Genio 360	Genio 420	Genio 520	Genio 720	GenioPro 5100	MT8875	MT8883	MT8893
Qwen3VL-2B	0.66 / 120.62 / 13.29	0.49 / 173.16 / 13.48	0.42 / 124.25 / 13.80	0.43 / 199.75 / 14.43	0.28 / 778.93 / 39.89	0.47 / 284.24 / 14.46	0.53 / 429.15 / 32.06	0.16 / 695.74 / 21.82
Qwen3VL-4B	–	–	–	–	0.28 / 500.40 / 19.73	–	–	0.22 / 480.36 / 11.21

Speech Recognition Performance Comparison

Note

Speech Recognition models are supported on both Android and Yocto.

Support Status

Model	Genio 360	Genio 420	Genio 520	Genio 720	GenioPro 5100	MT8875	MT8883	MT8893
Whisper-base (8w16a)	Q3/E	Q3/E	Q3/E	160.6 ms / 174.8 tok/s	By Request	By Request	By Request	By Request
Qwen3-ASR-0.6B	–	–	–	127.6 / 7.1 tok/s	Q4/E	Q4/E	Q4/E	Q4/E
Moonshine-Tiny	–	–	–	V	Q4/E	Q4/E	Q4/E	Q4/E

Android-only Models

The following model categories are supported on Android only and are not available on Yocto.

Note

Yocto support for these model categories is planned for 2026/E (estimated).

Stable Diffusion Performance Comparison

Performance Comparison (Main Time / Inference Time) (Unit: ms)

Model	Genio 360	Genio 420	Genio 520	Genio 720	GenioPro 5100	MT8875	MT8883	MT8893
Stable Diffusion v2.1 base model with controlnet	216219 / 143784	39995 / 38425	35480 / 30421	35461 / 30365	Q4/E	By Request	By Request	6969 / 5451
Stable Diffusion v.1.5 controlnet	65449 / 53267	43507 / 42111	34483 / 33057	33870 / 32763	Q4/E	Q4/E	Q4/E	6571 / 5262

CLIP Performance Comparison

Performance Comparison (Main Time / Inference Time) (Unit: ms)

Model	Genio 360	Genio 420	Genio 520	Genio 720	GenioPro 5100	MT8875	MT8883	MT8893
img_encoder_proj_clip_vit_large_dynamic	1362.52 / 435.94	619.67 / 421.55	488.69 / 314.31	473.82 / 309.29	Q4/E	Q4/E	Q4/E	358.61 / 51.14
img_encoder_proj_openclip_vit_h_dynamic	2440.64 / 1457.64	1760.07 / 1392.31	1376.49 / 1023.27	1331.19 / 1026.39	Q4/E	By Request	By Request	591.93 / 147.47
text_encoder_clip_vit_large	755.48 / 65.62	408.53 / 58.81	366.14 / 44.80	297.77 / 42.24	Q4/E	Q4/E	Q4/E	308.72 / 18.94
text_encoder_openclip_vit_h	1857.49 / 203.44	794.72 / 149.17	679.66 / 128.66	607.12 / 125.44	Q4/E	By Request	By Request	510.92 / 48.49

ONNX Runtime - Robotics AI

Important

MediaTek currently provides more comprehensive hardware-acceleration coverage for FP16 models in ONNX Runtime. Support for QDQ (INT8) quantization is under active development, and performance metrics will continue to optimize as operator coverage expands in future software releases.

The following tables list ONNX robotics models validated on Genio platforms, organized by robot capability. Measurements were obtained using the NPU Execution Provider (where available) with performance mode enabled.

For the complete model list with capability descriptions, see ONNX Runtime - Robotics AI.

Note

The following symbols are used in the tables below:

• -- : To be released.

• X : Platform does not support this model.

Robotics Models - Perception

Task	Model Name	Data Type	Input Size	G520 NPU (ms)	G520 CPU (ms)	G720 NPU (ms)	G720 CPU (ms)	Pretrained Model
Object detection	YOLOv5	–	–	–	–	–	–	–
Object detection	YOLOv8	–	–	–	–	–	–	–
Object detection	YOLO11n	–	–	–	–	–	–	–
Object detection	MobileNetV2	–	–	–	–	–	–	–
Object detection	SqueezeNet	–	–	–	–	–	–	–
Object detection	ResNet50	–	–	–	–	–	–	–
Object detection	MobileNetV3	–	–	–	–	–	–	–
Object detection	RT-DETR v2/v4	–	–	–	–	–	–	–
Object detection	RF-DETR	–	–	–	–	–	–	–
Image classification	ViT	–	–	–	–	–	–	–

Note

AGPL-3.0 License: YOLOv5, YOLOv8, and YOLO11n are licensed under AGPL-3.0 by Ultralytics. Pre-converted models are not directly provided due to copyleft license restrictions. For commercial closed-source use, obtain an Ultralytics Enterprise License (https://www.ultralytics.com/license) or use Apache-2.0 alternatives (YOLOX, RT-DETR, NanoDet).

Robotics Models - Interaction

Task	Model Name	Data Type	Input Size	G520 NPU (ms)	G520 CPU (ms)	G720 NPU (ms)	G720 CPU (ms)	Pretrained Model
Face recognition	VGGFace	–	–	–	–	–	–	–
Face recognition	MobileNetV3 embedding	–	–	–	–	–	–	–
Pose detection	MoveNet Lightning	–	–	–	–	–	–	–
Pose detection	RTMPose	–	–	–	–	–	–	–
Pose detection	HRNetPose	–	–	–	–	–	–	–
Pose detection	BlazePose Lite	–	–	–	–	–	–	–
Text recognition	PaddleOCR	–	–	–	–	–	–	–

Robotics Models - Navigation

Task	Model Name	Data Type	Input Size	G520 NPU (ms)	G520 CPU (ms)	G720 NPU (ms)	G720 CPU (ms)	Pretrained Model
Segmentation	Fast-SCNN	–	–	–	–	–	–	–
Segmentation	DeepLabv3	–	–	–	–	–	–	–
Segmentation	SeqFormer-B0	–	–	–	–	–	–	–
Segmentation	FastSAM	–	–	–	–	–	–	–
Segmentation	EdgeSAM	–	–	–	–	–	–	–
Single-camera depth	Depth Anything v2	–	–	–	–	–	–	–
Single-camera depth	Depth Anything v3	–	–	–	–	–	–	–
Dual-camera depth	SteroNet	–	–	–	–	–	–	–
Vision foundation model	DINOv2	–	–	–	–	–	–	–

Robotics Models - Audio

Task	Model Name	Data Type	Input Size	G520 NPU (ms)	G520 CPU (ms)	G720 NPU (ms)	G720 CPU (ms)	Pretrained Model
STT	Moonshine tiny (streaming)	–	–	–	–	–	–	–
TTS	ESPnet2	–	–	–	–	–	–	–
Ambient sound: echo cancellation	TBD (Coming soon)	–	–	–	–	–	–	–
Ambient sound: noise reduction	TBD (Coming soon)	–	–	–	–	–	–	–
Ambient sound: sound detection	YAMNet	–	–	–	–	–	–	–

Robotics Models - SLAM

Task	Model Name	Data Type	Input Size	G520 NPU (ms)	G520 CPU (ms)	G720 NPU (ms)	G720 CPU (ms)	Pretrained Model
Object tracking	BoxMOT	–	–	–	–	–	–	–
Localization	MobileNetVLAD	–	–	–	–	–	–	–
Localization	HFNet	–	–	–	–	–	–	–
Localization	SuperPoint	–	–	–	–	–	–	–
Localization	LightGlue	–	–	–	–	–	–	–

Robotics Models - Point Cloud

Task	Model Name	Data Type	Input Size	G520 NPU (ms)	G520 CPU (ms)	G720 NPU (ms)	G720 CPU (ms)	Pretrained Model
Point cloud detection	PointPillars-Tiny	–	–	–	–	–	–	–
Point cloud detection	CenterPoint-Tiny	–	–	–	–	–	–	–

Robotics Models - Others

Task	Model Name	Data Type	Input Size	G520 NPU (ms)	G520 CPU (ms)	G720 NPU (ms)	G720 CPU (ms)	Pretrained Model
Gaze estimation	UniGaze	–	–	–	–	–	–	–

Performance Notes

Performance can vary depending on:

• The specific Genio platform and hardware configuration.

• The version of the board image and evaluation kit (EVK).

• The selected backend and model variant.

To obtain the most accurate performance numbers for your use case, you must run the application directly on the target platform.