# Yolo Ultralytics stopped exporting fp16 tflite format. Can tflite-server directly handle fp32.tflite models?

Source: https://forum.modalai.com/topic/5356/yolo-ultralytics-stopped-exporting-fp16-tflite-format.-can-tflite-server-directly-handle-fp32.tflite-models
Category: General Questions (https://forum.modalai.com/category/2/general-questions)
Posted: 2026-07-30 16:44:48 UTC by arcj
Replies: 0 · Views: 95

## arcj · 2026-07-30 16:44:48 UTC

Hey ModalAI, 

Your documentation on custom inference using voxl-tflite-server is quite outdated. Yolo Ultralytics has stopped exporting frozen graph model format to tflite fp16 quantization. Ultralytics says there's no quantize=16 option — an FP32 .tflite model automatically runs in FP16 at runtime when using a GPU delegate (WebGPU/OpenCL/Metal), so a separate FP16 export file isn't needed. That's why half=True/quantize=16 throws the assertion.

Can voxl-tflite-server automatically execute FP32 models internally in FP16?
Hardware: VOXL2
Source code: Latest voxl-tflite-server code on modalai gitlab page.