TFLite(LiteRT) - Generative AI on GenioPro 5100

This page lists the generative AI models and representative performance data for GenioPro 5100 platforms. For background information about generative workloads and usage notes, refer to TFLite(LiteRT) - Generative AI.

Model Support and Performance

Note

Performance numbers apply to both Android and Yocto (this platform supports both OS). For OS-level GAI support across all platforms, see AI Supporting Scope.

The following symbols are used in the tables below:

  • -- : To be released.

  • By Request : Available by customer request only.

  • Q3/E : Support planned for Q3 end, 2026.

  • Q4/E : Support planned for Q4 end, 2026.

  • V : Supported and verified on this platform.

  • X : Platform does not support this model.

Large Language Models (LLMs)

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

Model

GenioPro 5100

Qwen3-0.6B

Q4/E

Qwen3-1.7B

Q4/E

Qwen3-4B

Q4/E

Qwen3-8B

536.44 / 8.44

Qwen2.5-1.5B-Instruct

By Request

Qwen2.5-3B-Instruct

By Request

Qwen2.5-7B-Instruct

By Request

gemma3-1B (Text Only)

Q4/E

gemma3-4B (Text-Only)

Q4/E

llama3.2-1B-Instruct

Q4/E

llama3.2-3B-Instruct

Q4/E

Phi-3-mini-4k-instruct

Q4/E

Phi-3.5-mini-instruct

Q4/E

Vision-Language Models (VLMs)

Performance Comparison (ViT Inference Time / Prompt / Generative)

Model

ViT Inference Time (s)

Prompt Mode (tok/s)

Generative Mode (tok/s)

Qwen3VL-2B

0.28

778.93

39.89

Qwen3VL-4B

0.28

500.40

19.73

Speech Recognition Models (ASR)

Performance Data

Model

GenioPro 5100

Whisper-base (8w16a)

By Request

Qwen3-ASR-0.6B

Q4/E

Moonshine-Tiny

Q4/E

Measured latency for these models is reported in asr_cmdline_tool, together with the transcripts each package’s sample clip is expected to produce.

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 and Image Generation

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

Model

GenioPro 5100

Stable Diffusion v2.1 base model with controlnet

Q4/E

Stable Diffusion v.1.5 controlnet

Q4/E

CLIP and Embedding Models

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

Model

GenioPro 5100

img_encoder_proj_clip_vit_large_dynamic

Q4/E

img_encoder_proj_openclip_vit_h_dynamic

Q4/E

text_encoder_clip_vit_large

Q4/E

text_encoder_openclip_vit_h

Q4/E