litert-community/yolox-nano-litert
object-detection model by litert-community
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
LiteRT is Google's on-device runtime, the new name for TensorFlow Lite (Android: com.google.ai.edge.litert:litert), and litert-torch, the renamed ai-edge-torch, is its PyTorch converter: a PyTorch model converted unmodified with literttorch.convert matched the original to 4e-7 on a Galaxy S26 (measured, LiteRT 2.2.0, Android 16, 2026-09-05). Megvii YOLOX-Nano (COCO, Apache-2.0) re-authored to a GPU-native LiteRT .tflite via the official literttorch path (no onnx2tf). FP16, 2.2 MB, input 416×416. Verified on a Pixel 8a: the whole graph runs on the GPU delegate (full LITERTCL residency, zero CPU fallback) and the GPU output matches the CPU/PyTorch reference (corr ≥ 0.999). YOLOX is a pure CNN, but its Focus stem (stride-2 space-to-depth slicing) lowers to GATHERND, which the GPU delegate rejects. Here the Focus + its following 3×3 conv are folded into a single, numerically-exact 6×6 stride-2 conv, so the graph has zero GATHER/GATHERND/ TopK/Cast ops and no >4D tensors. Activations (SiLU) lower to LOGISTIC+MUL.…
Read the full model card ↗ · Preview checked 2026-10-28T03:40:55.912Z
Inside the original model card — Document outline
- YOLOX-Nano — LiteRT (CompiledModel GPU)
- Why this is GPU-clean
- I/O
- Host-side decode (kept out of the graph for GPU-cleanliness)
- Minimal usage
- Performance
- Training data & PII
- Sample app + conversion script
- Performance
- Snapdragon NPU (Hexagon)
- Raspberry Pi 5 (CPU)
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
litert-community/yolox-nano-litert is a object-detection model repository published by litert-community on Hugging Face. The source reports the litert library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- object-detection
- Library
- litert
- Recent downloads (30 days)
- 1,756
- Cumulative likes
- 2
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-06-27T11:37:25.000Z
- Last modified
- 2026-09-05T10:14:52.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:54:34.007Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
mudler/locate-anything.cpp-gguf
microsoft/table-transformer-structure-recognition
PekingU/rtdetr_r101vd_coco_o365