plantnet-300k-resnet18 — LiteRT.js demo

Source	https://huggingface.co/litert-community/PlantNet-300K-ResNet18-LiteRT
License	apache-2.0
Model file	`caf1eeeaf4ec2dcba88146cbce7b0ae9fe7b9dfdcaa6a151dbc29034fbdf0c49.tflite` — downloaded from the source at runtime; this site hosts no weights

Run it in your browser

Measured sweep results

Every number is labeled with the environment that produced it — headless desktop Chromium is not a user’s phone, and results are only meaningful together with their environment.

Backend	Status	Full delegation	Output match	Latency p50 (ms)	Environment	Verified	Provenance
`wasm_xnnpack`	pass	—	—	52.538	mac-studio-m4-max · chromium 151.0.7922.34 headless · macOS · @litertjs/core 2.5.3	2026-08-11	measured
`webgpu_mldrift`	pass	yes	pass	2.665	mac-studio-m4-max · chromium 151.0.7922.34 headless · macOS · @litertjs/core 2.5.3	2026-08-11	measured

Build this yourself

One-line prompt for your AI coding assistant (uses the litert-cookbook web skill):

Use the litert-cookbook web skill to build a LiteRT.js browser demo for plantnet-300k-resnet18: load the model from https://huggingface.co/litert-community/PlantNet-300K-ResNet18-LiteRT/resolve/main/caf1eeeaf4ec2dcba88146cbce7b0ae9fe7b9dfdcaa6a151dbc29034fbdf0c49.tflite (license: apache-2.0) and run it with @litertjs/core.

Reproduce this with an agent

One-line prompt for Claude Code / Gemini CLI — re-runs the same sweep verification for this model, locally:

In the edge-compat repo, verify plantnet-300k-resnet18 with the sweep harness: write /tmp/catalog.csv with the header line model_id,source,input_spec,license,notes and the single row plantnet-300k-resnet18,https://huggingface.co/litert-community/PlantNet-300K-ResNet18-LiteRT/resolve/main/caf1eeeaf4ec2dcba88146cbce7b0ae9fe7b9dfdcaa6a151dbc29034fbdf0c49.tflite,1x3x224x224:float32,apache-2.0, — then run: cd web/sweep && npm ci && npm run sweep -- --catalog /tmp/catalog.csv --out out/ — and compare out/plantnet-300k-resnet18.json with the sweep table on this page.