On-device intelligence.
☆397Mar 24, 2025Updated last year
Alternatives and similar repositories for edge
Users that are interested in edge are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The official Cartesia client for Python.☆121Mar 16, 2026Updated last week
- Developer showcase of projects built on Cartesia☆20Aug 28, 2024Updated last year
- Cartesia Line SDK for voice agents.☆95Mar 12, 2026Updated last week
- The JavaScript client for the Cartesia API.☆128Mar 16, 2026Updated last week
- On-device semantic search over Apple WWDC 2025 docs using MLX embeddings — SwiftUI app (WWDC OMT 2025)☆76Jun 12, 2025Updated 9 months ago
- entropix style sampling + GUI☆27Oct 30, 2024Updated last year
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆15Apr 30, 2025Updated 10 months ago
- ☆27Jul 9, 2024Updated last year
- ☆19Dec 4, 2025Updated 3 months ago
- ☆13Dec 15, 2025Updated 3 months ago
- ☆28Mar 17, 2023Updated 3 years ago
- Code for the paper: https://arxiv.org/pdf/2309.06979.pdf☆21Jul 29, 2024Updated last year
- ☆30Feb 27, 2024Updated 2 years ago
- ☆54May 20, 2024Updated last year
- PyTorch implementation of models from the Zamba2 series.☆189Jan 23, 2025Updated last year
- Voice agent using LiveKit (orchestration), Cartesia (TTS), OpenAI (LLM), and Deepgram (STT)☆20Oct 28, 2025Updated 4 months ago
- A fast multimodal LLM for real-time voice☆4,381Dec 12, 2025Updated 3 months ago
- Grokking on modular arithmetic in less than 150 epochs in MLX☆16Oct 24, 2024Updated last year
- FastMLX is a high performance production ready API to host MLX models.☆347Mar 18, 2025Updated last year
- Understand and test language model architectures on synthetic tasks.☆263Updated this week
- Supporting code for "LLMs for your iPhone: Whole-Tensor 4 Bit Quantization"☆11Mar 31, 2024Updated last year
- ☆209Dec 11, 2024Updated last year
- train with kittens!☆64Oct 25, 2024Updated last year
- Joint speech-language model - respond directly to audio!☆373Jul 1, 2024Updated last year
- Open Source framework for voice and multimodal conversational AI☆10,821Updated this week
- Run Time Series Foundation Models on Apple Silicon☆31Feb 27, 2026Updated 3 weeks ago
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,420Apr 21, 2025Updated 11 months ago
- A basic voice agent built with Node.js agents framework☆35Oct 1, 2025Updated 5 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆665Feb 6, 2026Updated last month
- Joint speech-language model - respond directly to audio!☆30May 13, 2024Updated last year
- ☆337Mar 5, 2026Updated 2 weeks ago
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆250Jun 6, 2025Updated 9 months ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32May 25, 2024Updated last year
- A simple frontend page to interact with an OpenAI like API☆16Jan 31, 2025Updated last year
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,630Updated this week
- ☆33Nov 21, 2025Updated 4 months ago
- Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audi…☆9,898Mar 4, 2026Updated 2 weeks ago
- MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.☆2,309Mar 18, 2026Updated last week
- ☆20Sep 6, 2025Updated 6 months ago