On Device Ai Python Packages

litert-lm-builder

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

veloxquant-mlx

Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels

litert-lm-api

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

litert-lm-api-nightly

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

litert-lm

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

deepbom

Local static analysis and evidence generation for deployed AI model artifacts

termux-stt

🎙️ Production-grade On-Device Speech-to-Text & 128d X-Vector Speaker Diarization for Android Termux. whisper.cpp, Vosk, Sherpa-ONNX, and 0 PyTorch Dependency.

ameva-runtime

Unified Next-Gen Hardware Orchestration & AI Acceleration Runtime for Mobile & Edge

termux-diffusion

AmfyUI (ComfyUI Mobile DAG Studio) & Z-Image Turbo (6.0B DiT) On-Device Diffusion Runtime for Android Termux

circle-schema

On-device Neural Engine

litert-lm-builder-nightly

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

ax-engine

One Mac process. Many models. Real speed. Multi-model LLM serving with prefix reuse, MTP acceleration, and OpenAI APIs — built for Apple Silicon, measured against mlx-lm and llama.cpp.

litert-lm-nightly

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

termux-train

📱 Ultra-lightweight On-Device Tensor & DAG Autograd Deep Learning Framework for Android ARM64 Termux. SafeTensors zero-copy, LoRA fine-tuning, and RoPE Transformers.

termux-tts

🗣️ Production-grade On-Device Text-to-Speech Framework for Android Termux (DSP Formant Vocoder, ONNX Neural Runtime & Android Native Voice Bridge)

torchnative

Run the real PyTorch ecosystem on device, not reimplementing it

laya-coreml

Local Laya typed decisions on Apple Core ML and Neural Engine. Validated ports, ~5 ms short decisions on M3 Max, reproducible speed and energy benchmarks.

edge-proc

For Python apps that ship data to devices: each one checks it's genuine, downloads only changes, and searches offline.

termux-vision

🚀 The Sovereign On-Device Computer Vision & Multimodal VLM Inference Engine for Android Termux & ARM64 (Dual-Engine Python & Node.js/TypeScript)

edgejev

离线可用的本地类型化决策：4 核 CPU 单题 15.6ms。Local & offline Jev / System One inference on CPU — ONNX + INT8, no torch at runtime. 支持 laya / kev / PlayJev

nobodywho

NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

cactus-compute

Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.

pixcull

Local-first AI photo culling for professional photographers — 6-axis rubric, XMP/IPTC export, Lightroom & Capture One ready.

onert

On-device Neural Engine