TFLite(LiteRT) - Generative AI on Genio 720
This page lists the generative AI models and representative performance data for Genio 720 platforms. For background information about generative workloads and usage notes, refer to TFLite(LiteRT) - Generative AI.
Model Support and Performance
The following tables summarize the supported generative models and measured performance on Genio 720.
Prompt Mode (tok/s) |
Generative Mode (tok/s) |
|
DeepSeek-R1-Distill-Llama-8B |
36.653 |
4.578 |
DeepSeek-R1-Distill-Qwen-1.5B |
341.686 |
11.764 |
DeepSeek-R1-Distill-Qwen-7B |
69.23 |
4.677 |
gemma2-2b-it |
193.392 |
8.752 |
internlm2-chat-1_8b |
276.218 |
17.549 |
llama3-8b |
56.495 |
4.698 |
llama3.2-1B-Instruct |
401.288 |
24.533 |
llama3.2-3B-Instruct |
154.557 |
10.577 |
Qwen2-0.5B-Instruct |
762.455 |
50.06 |
Qwen2-1.5B-Instruct |
341.993 |
19.563 |
Qwen2-7B-Instruct |
70.416 |
4.883 |
Qwen1.5-1.8B-Chat |
310.639 |
9.895 |
Qwen2.5-1.5B-Instruct |
341.418 |
18.427 |
Qwen2.5-3B-Instruct |
162.481 ok/s |
10.31 |
Qwen2.5-7B-Instruct |
70.548 |
4.892 |
Qwen3 1.7B |
233.032 |
10.911 |
Phi-3-mini-4k-instruct |
129.6 |
7.324 |
MiniCPM-2B-sft-bf16-llama-format |
194.793 |
7.694 |
medusa_v1_0_vicuna_7b_v1.5 |
91.821 |
10.564 |
vicuna1.5-7b-tree-speculative-decoding-plus |
84.895 |
12.6489 |
llava1.5-7b-speculative-decoding |
73.103 |
7.281 |
baichuan-7b-int8-cache |
81.184 |
4.239 |
baichuan-7b |
79.745 |
4.182 |
ViT Inference Time (s) |
Prompt Mode (tok/s) |
Generative Mode ( tok/s) |
|
Qwen2.5 VL 3B |
0.208 |
100.065 |
4.776 |
InternVL3-1B |
1.744 |
74.748 |
6.157 |
Main Time (ms) |
Inference Time (ms) |
|
Stable Diffusion v.1.5 |
25816 |
24813 |
Stable Diffusion v.1.5 controlnet |
33642 |
32294 |
Stable_diffusion_v1_5_controlnet_lora |
34148 |
32454 |
Stable_diffusion_v1.5_2lora |
35978 |
33195 |
Stable Diffusion v2.1 base model with controlnet |
31183 |
29828 |
Stable Diffusion v1.5 LCM Ipadaptor |
10645 |
5861 |
Stable_diffusion_lcm_multiDiffusion |
29103.565 |
28126.856 |
Main Time (ms) |
Inference Time (ms) |
|
CLIP Image Encoder |
||
img_encoder_proj_clip_vit_large_dynamic |
567.61 |
257.388 |
img_encoder_proj_openclip_vit_big_g_dynamic |
12035.52 |
3142.959 |
img_encoder_proj_openclip_vit_h_dynamic |
1440.197 |
881.647 |
CLIP Text Encoder |
||
text_encoder_clip_vit_large |
455.079 |
38.993 |
text_encoder_openclip_vit_h |
750.703 |
119.77 |