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.
☆134Aug 23, 2026Updated 2 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:
- Apple Neural Engine (ANE) LLM inference engine — reverse-engineered private APIs, Metal GPU shaders, hybrid ANE+GPU+CPU on Apple Silicon.…☆34Oct 2, 2026Updated last month
- Run transformers directly on Apple's Neural Engine in Swift bypass coreml entirely☆176Sep 12, 2026Updated 2 months ago
- ☆86Mar 3, 2026Updated 8 months ago
- ☆30Oct 31, 2026Updated 2 weeks ago
- Python runtime for the Apple Neural Engine☆77Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Research MIL-to-HWX compiler for the M4 Apple Neural Engine☆19Sep 3, 2026Updated 2 months ago
- ☆47Nov 12, 2026Updated last week
- A compiler that converts ML models to optimized executables☆10Dec 25, 2024Updated last year
- Artificial Neural Engine Machine Learning Library☆1,709Oct 31, 2026Updated 2 weeks ago
- Apple Silicon gputrace analysis tool☆26Sep 2, 2026Updated 2 months ago
- Benchmarking the new Neural Accelerator hardware of A19 chips☆17Oct 19, 2025Updated last year
- LLM inference on Apple Neural Engine (ANE)☆147Mar 4, 2026Updated 8 months ago
- ☆24Oct 27, 2025Updated last year
- Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU☆209Updated this week
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- DFlash block-diffusion speculative decoding running on Apple Silicon via MLX, with an ANE execution path that explores heterogeneous acce…☆62Apr 18, 2026Updated 7 months ago
- Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon☆53Mar 31, 2026Updated 7 months ago
- Training neural networks on Apple Neural Engine via reverse-engineered private APIs☆7,305Mar 10, 2026Updated 8 months ago
- a quick and dirty little program to convert Apple CoreML model to ANE hwx file☆55Nov 6, 2026Updated 2 weeks ago
- Apple Silicon GPU DVFS reverse engineering: voltage corners, CLPC frequency control, Metal benchmarks☆74Oct 30, 2026Updated 2 weeks ago
- ☆13Jul 24, 2026Updated 3 months ago
- ☆229Mar 24, 2026Updated 7 months ago
- Utilities to evaluate MLX quantizations☆26Jun 9, 2026Updated 5 months ago
- llama.cpp fork for running Qwen3.8-Flash-Next V3 (95.5 GiB) on a 64 GB Apple Silicon Mac by streaming MoE experts from SSD. Setup guide: …☆13Sep 19, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- 🚀 LLM inference Engine in Swift/Metal, Load GGUF and safe tensors modes, no conversion, no cpp, pure swift☆51May 19, 2026Updated 6 months ago
- LLM training on Apple's Neural Engine — native Obj-C, private APIs, zero GPU. Dynamic weight pipeline for training without kernel recompi…☆59Mar 17, 2026Updated 8 months ago
- Reverse engineered the Apple Neural Engine, with working Python and Objective C samples☆41Feb 1, 2026Updated 9 months ago
- Test Apple Neural Engine☆38Nov 10, 2018Updated 8 years ago
- Lossless DFlash speculative decoding for MLX on Apple Silicon☆793Aug 20, 2026Updated 3 months ago
- Raw-Metal inference engine for Qwen3.8-Flash-Next on Apple M5: EXL3 weights, MTP, OpenAI + Anthropic APIs☆14Oct 23, 2026Updated 3 weeks ago
- ☆17Apr 17, 2026Updated 7 months ago
- Flash-MoE sidecar slot-bank runtime for large GGUF MoE models on Apple Silicon — llama.cpp fork☆135Oct 7, 2026Updated last month
- ☆13Apr 8, 2026Updated 7 months ago
- 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.
- Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers☆30May 19, 2026Updated 6 months ago
- Implementation of ESRGAN using TensoFlow☆18Jan 15, 2020Updated 6 years ago
- Automated management of ad campaigns in Google Display&Video 360.☆15Feb 9, 2026Updated 9 months ago
- ☆37Mar 30, 2026Updated 7 months ago
- ☆13Apr 14, 2025Updated last year
- The ultimate training toolkit for finetuning diffusion models☆34Jan 22, 2026Updated 9 months ago
- EXO Gym is an open-source Python toolkit that facilitates distributed AI research.☆120Dec 1, 2025Updated 11 months ago
Are these results useful?