Skip to main content

29 docs tagged with "SL2610"

View all tags

EmbeddingGemma-2 INT8

A multimodal embedding model from Google that maps text, images, video and audio into one 768-dimensional space for cross-modal search, optimized for the Torq NPU.

Face ID INT8

A three-stage on-device face recognition pipeline: face detection, 68-point facial keypoints, and 256-D face embeddings.

FunctionGemma 270M IT

A lightweight 270M parameter model from Google, built on Gemma 3 270M and trained for function calling, intended as a foundation for specialized fine-tuned models.

Gemma3 270M IT

A compact 270M parameter multimodal language model from Google optimized for text classification and data extraction tasks with rapid fine-tuning capability.

Gemma3 270M IT INT4

A compact 270M parameter language model from Google, quantized to INT4, for text classification and data extraction tasks with rapid fine-tuning capability.

LiquidAI LFM2-VL 450M BF16

A 450M parameter vision-language model from Liquid AI that answers natural-language questions about an input image.

LiquidAI LFM2.5 230M BF16

A 230M parameter hybrid short-convolution and attention language model from Liquid AI that can act as a skill-selection layer, decomposing instructions into tool calls.

MobileNet V2 224x224 INT8

A quantized MobileNet V2 model with a 1.0 width multiplier optimized for image classification on ImageNet at 224x224 resolution.

Moonshine Streaming Tiny

A streaming automatic speech recognition model with a sliding-window encoder for low time-to-first-token, optimized for 16kHz mono audio.

Moonshine Tiny BF16

A high-efficiency automatic speech recognition model using variable-length architecture for real-time speech recognition, optimized for 16kHz mono audio.

Qwen3 0.6B GPTQ INT4

A 0.6B parameter language model from the Qwen team, quantized to INT4 with GPTQ for the Torq NPU.

Torq Introduction

An overview of the Torq Edge AI platform for running neural networks on the SL2610 NPU.

YOLO26 320x320 INT8

YOLO26 NMS-free object detection models (nano) optimized for 320x320 resolution, with the decode head compiled onto the NPU.

YOLO26 320x320 INT8

YOLO26 NMS-free object detection models (small) optimized for 320x320 resolution, with the decode head compiled onto the NPU.

YOLOv8n Nano 320x320 INT8

A YOLOv8n model for object detection optimized for 320x320 resolution, offering a balance between speed and accuracy.

YOLOv8s Small 320x320 INT8

A YOLOv8s model for object detection optimized for 320x320 resolution, offering a balance between speed and accuracy.