hustvl

/

yolos-tiny

like 281

Follow

HUST Vision Lab 133

Great work on this model! 👋

At Dispatch AI (FZE, UAE), we benchmark models on 40 phones (Snapdragon 865). We're always looking for models that can run on mobile.

Question for @hustvl (or anyone who's tested this):

1. What's the expected inference speed on ARM processors?
2. Has anyone quantized this to GGUF/ONNX?
3. What's the minimum RAM needed?

If you're interested, we'd love to benchmark it on our phone farm and share results publicly.

• Dispatch AI (FZE), Sharjah UAE