Models

An INT8-quantized GoogLeNet image classification model based on an Inception-style convolutional architecture. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

This is an INT8-quantized version of YOLO11n optimized for edge deployment on ARM devices using ExecuTorch with the XNNPACK backend. The model was quantized using PT2E static symmetric per-channel quantization and exported to the .pte format for efficient inference on ARM Cortex-A processors (AWS Graviton, mobile ARM, embedded, Raspberry Pi).

This is an INT8-quantized version of yolo11n-pose (Ultralytics) optimized for edge deployment on ARM devices using ExecuTorch with the XNNPACK backend. The model was quantized using PT2E static quantization and exported to the .pte format for efficient inference on ARM Cortex-A processors (Raspberry Pi 5, mobile ARM, embedded).

An INT8-quantized YAMNet audio classification model for recognizing sound events. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

INT8-quantized 18-layer residual network for 1000-class image classification, optimized for efficient ARM edge inference with ExecuTorch and the XNNPACK backend. It uses 224×224 RGB inputs with ImageNet normalization and returns logits for top-k prediction, offering a much smaller, faster, and lower-memory alternative to the FP32 baseline while retaining comparable classification quality.

This is an INT8-quantized version of YOLOX-s optimized for edge deployment on ARM devices using ExecuTorch with the XNNPACK backend. The model was quantized using PT2E static quantization and exported to the .pte format for efficient inference on ARM Cortex-A processors (AWS Graviton, mobile ARM, embedded).

An INT8-quantized TinyLlama 1.1B Chat causal language model for conversational text generation. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

An INT8-quantized GoogLeNet image classification model based on an Inception-style convolutional architecture. Exported as an ExecuTorch program using the Ethos-U delegate for inference on Arm Ethos-U NPUs.

An INT8-quantized YOLOX-S single-stage, anchor-free object detection model for locating and classifying objects in images. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

A 50-layer residual convolutional neural network for 1000-class image classification, using INT8 per-tensor quantization to reduce size and computation while preserving strong accuracy. It accepts 224×224 RGB inputs with ImageNet-style preprocessing and produces raw logits over 1,000 categories.

This is an INT8-quantized version of YOLO26s, Ultralytics' NMS-free, end-to-end object detector with a one2one Detect head. It is optimized for edge deployment on ARM devices using ONNX Runtime, whose CPU execution provider dispatches INT8 GEMMs to MLAS and KleidiAI on aarch64. The detection head is left quantizable; PT2E-forced shared-scale Q/DQ artifacts around concatenation and permute ops in the head are stripped after conversion to preserve mixed-range box/score outputs.

An INT8-quantized DETR object detection model combining a ResNet-50 backbone with a transformer-based detection architecture. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

INT8-quantized automatic speech recognition model for English speech-to-text, based on an encoder-decoder Transformer architecture with autoregressive decoding and KV caching. It uses 128-bin log-mel audio features and produces text transcriptions via greedy decoding, with weight-only quantization designed to reduce model size while preserving transcription quality.

An INT8-quantized monocular depth estimation model that predicts relative inverse-depth maps from single RGB images. It uses a ResNet-based backbone and produces dense depth outputs suitable for applications such as AR/VR, robotics, novel-view synthesis, and image editing. Inputs are resized RGB images, and outputs are relative depth maps requiring calibration for metric depth.

An INT8-quantized QuickSRNetSmall image super-resolution model for upscaling low-resolution images. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

An INT8-quantized Gemma 2 2B causal language model for text generation. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

An INT8-quantized Qwen2.5 0.5B Instruct causal language model for instruction-following and text generation. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

An INT8-quantized Phi-3.5 Mini language model for text generation. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

A compact decoder-only causal language model for text generation, using INT4 weight quantization with dynamic INT8 activations and INT8 embeddings to reduce size and memory use while preserving practical language capabilities. It supports raw prompt continuation and in-context few-shot tasks without chat formatting.

An INT8-quantized BGE Base EN v1.5 English text embedding model for semantic search, retrieval, and similarity tasks. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

An INT8-quantized Llama 3.1 8B Instruct causal language model for instruction-following and text generation. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

Hy-MT2-1.8B machine translation optimized as a Q4_0 GGUF model for llama.cpp on Arm-based Premium Smartphone systems.

An INT8-quantized single-stage object detector for 80 COCO classes, using an anchor-free architecture with 640×640 RGB inputs. It outputs bounding boxes and class scores for common objects, with postprocessing via confidence filtering, box conversion, and per-class non-maximum suppression.

An INT8-quantized YOLOX-S single-stage, anchor-free object detection model for locating and classifying objects in images. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

A compact decoder-only causal language model for text generation, using INT4 quantized linear weights with dynamic INT8 activations and tied INT8 block-quantized embeddings/LM head. It is designed for efficient continuation and few-shot prompting with a large SentencePiece vocabulary, offering reduced memory footprint and faster CPU inference while retaining the behavior of a base, non-instruction-tuned model.

An INT8-quantized Wide ResNet-50 image classification model using a widened residual convolutional network for visual feature extraction. Exported as an ExecuTorch program using the XNNPACK backend for inference on Arm CPUs.

An INT8-quantized, lightweight segment-anything image segmentation family with a compact TinyViT backbone, designed for box-prompted instance mask generation. It produces multiple candidate masks with IoU quality scores from RGB images and bounding-box prompts, offering reduced size and memory use while preserving high mask quality.