Local AI runtime for training & running small LLMs directly on Apple Neural Engine (ANE). No CoreML. No Metal. Offline, on-device fine-tuning & inference on M-series silicon.
☆110Mar 6, 2026Updated 4 months ago
Alternatives and similar repositories for Orion
Users that are interested in Orion are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ANE (Apple Neural Engine) CostModel profiler for CoreML models☆33Apr 9, 2026Updated 3 months ago
- Apple Neural Engine (ANE) LLM inference engine — reverse-engineered private APIs, Metal GPU shaders, hybrid ANE+GPU+CPU on Apple Silicon.…☆22Mar 5, 2026Updated 4 months ago
- Train and run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely☆153Updated this week
- ☆86Mar 3, 2026Updated 4 months ago
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆62Apr 18, 2026Updated 3 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU☆177Jun 8, 2026Updated last month
- ☆42Mar 5, 2026Updated 4 months ago
- Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon☆47Mar 31, 2026Updated 3 months ago
- Flash-MoE sidecar slot-bank runtime for large GGUF MoE models on Apple Silicon — llama.cpp fork☆118Updated this week
- Artificial Neural Engine Machine Learning Library☆1,628Mar 10, 2026Updated 4 months ago
- Prototype for a SPIR-V assembler and dissasembler. It provides a composable Java interface for generating SPIR-V code at runtime.☆15Oct 31, 2025Updated 8 months ago
- Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers☆29May 19, 2026Updated 2 months ago
- Training neural networks on Apple Neural Engine via reverse-engineered private APIs☆6,933Mar 10, 2026Updated 4 months ago
- PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal ac…☆306Jun 5, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆35Mar 30, 2026Updated 3 months ago
- ☆13Apr 14, 2025Updated last year
- ☆219Mar 24, 2026Updated 3 months ago
- An MLX port of Meta's Coconut reasoning model☆16Sep 2, 2025Updated 10 months ago
- Explorations into the proposed SDFT, Self-Distillation Enables Continual Learning, from Shenfeld et al. of MIT☆31Feb 6, 2026Updated 5 months ago
- A repo of useful MLX skills.☆87Jan 25, 2026Updated 5 months ago
- LLM training on Apple's Neural Engine — native Obj-C, private APIs, zero GPU. Dynamic weight pipeline for training without kernel recompi…☆56Mar 17, 2026Updated 4 months ago
- A Swift port of Andrej Karpathy‘s llm.c.☆28Mar 10, 2025Updated last year
- Rust-native hybrid training & inference engine for Apple Neural Engine + Metal GPU☆179Apr 3, 2026Updated 3 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- An MLX implementation of Meta AI's ESM-2 protein language model☆16Aug 16, 2025Updated 11 months ago
- EXO Gym is an open-source Python toolkit that facilitates distributed AI research.☆115Dec 1, 2025Updated 7 months ago
- 🚀 LLM inference Engine in Swift/Metal, Load GGUF and safe tensors modes, no conversion, no cpp, pure swift☆45May 19, 2026Updated 2 months ago
- Headless terminal emulator CLI powered by libghostty-vt☆18Apr 8, 2026Updated 3 months ago
- Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port wi…☆146Apr 15, 2026Updated 3 months ago
- vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon☆275Jun 3, 2026Updated last month
- Train Large Language Models on MLX.☆401Updated this week
- Metal Flash Attention for MLX☆19Jul 14, 2026Updated last week
- A Swift package for interacting with selenium and undetected-chromedriver through python by using PythonKit.☆13Jun 21, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unslot…☆1,364Jun 23, 2026Updated 3 weeks ago
- Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS (E2 TTS) in MLX☆29Oct 15, 2024Updated last year
- Run embedding models locally in Swift using MLTensor.☆151Jun 8, 2026Updated last month
- ☆42Apr 5, 2026Updated 3 months ago
- NEW v1.1: https://github.com/dstolz/epsych_v1.1 Epsych is a toolbox for extending Tucker-Davis Technologies hardware and sof…☆15Apr 14, 2022Updated 4 years ago
- Semantic Regex☆18Nov 13, 2025Updated 8 months ago
- Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives C…☆28Jun 29, 2026Updated 3 weeks ago