---
license: agpl-3.0
pipeline_tag: image-segmentation
tags: [Agora, QNN, AIoT, Qualcomm]
---

# FastSAM-S model resources

FastSAM-S，使用 Model Farm 官方预处理与样例，逐板卡验证。

Board builds that [Agora](https://mega.aidlux.com) runs and measures on real Qualcomm boards. Try it online, without a board: https://mega.aidlux.com/models/fastsam-s

| SoC · board | Precisions | Measured on Agora (default precision) |
| --- | --- | --- |
| QCS6490 · 犀牛派 A1 (Rhino Pi A1) | W8A16, W8A8 | 13.8 ms |
| QCS8550 · 犀牛派 X1 (Rhino Pi X1) | FP16, W8A16, W8A8 | 8.8 ms |

Task: 分割. Inputs: image (image). Outputs: masks (masks).

## Download

```bash
export AGORA_WORKSPACE="$HOME/my-fastsam-s"
export AGORA_SOC='QCS8550'
hf download APLUX-Agora/FastSAM-S \
  --include "targets/$AGORA_SOC/*" --local-dir "$AGORA_WORKSPACE/resources"
```

Each `targets/<SoC>/` holds `model.json` (default precision and variant paths) and one directory per precision. Context binaries are named `model.bin`; multi-file packages are kept as published by Model Farm.

Pre- and post-processing, the runner and an exported project: open the model on Agora and choose “部署指南”, or export any workflow that uses it.

## Licence and provenance

Source model licence: AGPL-3.0 (see LICENSE). 
Converted, deployable resources: APLUX Model Farm License (LICENSE_MODEL_FARM.pdf). See NOTICE.md and SHA256SUMS.