TCL Smart TV Pro
4× Cortex-A73 @ 1.39 GHz, 32-bit userspace, 2.4 GB RAM (~700 MB free), Mali-G52 GPU, MDLA NPU via NNAPI (mtk-mdla_shim). Suspends ~3 min after power-off.
- Manufacturer
- TCL
- SoC
- MediaTek MT9689
- OS
- Google TV (Android 14)
- RAM
- 2.4 GB
- Accelerators
- NPU, GPU, CPU
8 results
efficientnet-lite0-int8NPU · nnapi:mtk-mdla_shim
6 msWorksinvoke time
version 1.0.0 · 2026-11-18
efficientnet-lite2-int8NPU · nnapi:mtk-mdla_shim
9.4 msWorksinvoke time
version 1.0.0 · 2026-11-18
mobilenet-v2-int8NPU · nnapi:mtk-mdla_shim
4.4 msWorks4.4–5.0 ms invoke
version 1 · 2026-11-18
efficientnet-lite4-int8NPU · nnapi:mtk-mdla_shim
22 msWorks with tweaksTweak: Load the model from a memory-mapped buffer, not a path on shared storage: SELinux blocks the NN HAL (mtk_hal_neuralnetworks) from reading FUSE files, and NNAPI then silently falls back to its CPU reference path (~9 s per image).
invoke p50 22 ms; full request (decode, render, pack, invoke) ~72 ms
version 1.0.0 · 2026-11-18
mobilenet-v2-fp32NPU · nnapi:mtk-mdla_shim
11.2 msWorks with tweaksTweak: Enable allow_fp16 on the NNAPI delegate (setAllowFp16(true)).
11.2 ms invoke with fp16 relaxation
version 1 · 2026-11-18
clip-vit-b16Unknown · n/a
–Failsfp32, 330 MB: out of memory while loading; the TV rebooted.
version 1 · 2026-11-18
clip-vit-b16GPU · gpu (Mali-G52 delegate)
–FailsThe GPU delegate does not support the graph (unsupported CONCATENATION).
version 1 · 2026-11-18
mobilenet-v2-fp32NPU · nnapi:mtk-mdla_shim
–FailsThe MDLA does not run fp32 graphs; without allow_fp16 NNAPI rejects the model for the NPU.
version 1 · 2026-11-18