PyPI Stats

On Device Ai Python Packages

Python packages with the GitHub topic on-device-ai. Sorted by relevance, with stars and monthly downloads.
Samsung
circle-schema

On-device Neural Engine

14K 566 178
ARahim3
mlx-tune

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

11K 1K 79
Samsung
onert

On-device Neural Engine

7K 566 178
nobodywho-ooo
nobodywho

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

4K 868 58
Samsung
sg1ab

On-device Neural Engine

3K 566 178
dualform-labs
m5-infer

Extraordinary speed, extraordinary quality — an MLX-based inference engine for Apple Silicon.

2K 0 1
appautomaton
mlx-speech

Pure-MLX speech synthesis, voice cloning, dialogue, sound-effects, and ASR for Apple Silicon — Fish S2 Pro, VibeVoice, LongCat, MOSS, Step-Audio, Cohere ASR.

1K 13 3
notolog
notolog

Notolog Markdown Editor

951 25 6
Samsung
model-explorer-circle

On-device Neural Engine

813 566 178
sym-bot
mesh-cognition

Python coupling kernel for Mesh Cognition — per-field admission and state blending for CfC neural networks. Canonical home: meshcognition.org

706 0 0
wild-edge
wildedge-sdk

Python SDK for WildEdge

653 13 1
ARahim3
unsloth-mlx

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

513 1K 79
facebookresearch
edgetam-dimos

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

473 921 72
vibeinging
memme

Edge-first AI memory engine powered by DuckDB

220 1 0
NexaAI
nexaai-metal

Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.

129 8K 997
sym-bot
langchain-mesh-cognition

LangChain integration for Mesh Cognition — give any agent distributed memory across devices

108 0 0
NexaAI
nexaai-gpu

Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.

65 8K 997
NexaAI
nexai

Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.

39 8K 997
Samsung
nnfw-api-pybind

On-device Neural Engine

1 566 178