# Project A.E.S.I.R. — Native Mojo AI Inference Engine for running local LLMs

**URL:** https://forum.modular.com/t/project-a-e-s-i-r-native-mojo-ai-inference-engine-for-running-local-llms/3500
**Category:** Community Showcase
**Created:** [September 16, 2026, 5:17pm UTC](https://forum.modular.com/t/project-a-e-s-i-r-native-mojo-ai-inference-engine-for-running-local-llms/3500 "2026-09-16T17:17:36Z")
**Posts on this page:** 1
**Page:** 1

<div class="post-metadata">

### Author: ![VolmarrViking](https://sea1.discourse-cdn.com/flex001/user_avatar/forum.modular.com/volmarrviking/32/1273_2.png) [@VolmarrViking](https://forum.modular.com/u/VolmarrViking)
#### Post date: [September 16, 2026, 5:17pm UTC](https://forum.modular.com/t/project-a-e-s-i-r-native-mojo-ai-inference-engine-for-running-local-llms/3500/1 "2026-09-16T17:17:36Z")

</div>

**Project A.E.S.I.R. is an experimental native-Mojo engine for running local AI models directly on your own hardware** , and it is evolving from a working low-level inference engine into a practical backend that ordinary AI applications can eventually use.

**Right now** , A.E.S.I.R. can **already run real GGUF language models through native Mojo on both CPU and NVIDIA GPUs** , hold conversations with them locally, manage and inspect models, download models from Hugging Face, and serve them through working Ollama- and OpenAI-compatible APIs.

**Development is moving quickly** , with plans to expand A.E.S.I.R. across many more model families, quantization formats, GPUs, CPUs, NPUs and edge devices, while adding richer application compatibility, smarter heterogeneous hardware use, advanced memory and inference optimizations, multimodal AI, and eventually a foundation for more ambitious local machine-cognition systems.

**Developers and testers are very welcome** to join the forge, whether by adding support, improving the runtime, testing new model families and quantizations, or **helping get additional hardware backends properly tested, documented, and proven with reproducible evidence**.

> **[GitHub - hrabanazviking/RuneForgeAI-Project-Aesir: Bare-metal Mojo inference engine designed for...](https://github.com/hrabanazviking/RuneForgeAI-Project-Aesir)**
>
> Bare-metal Mojo inference engine designed for local sovereignty. Features zero-copy GGUF parsing, PagedAttention KV caching, and a stateless sampler. Optimized for consumer hardware, it eliminates cloud dependency and bloat to deliver high-performance, private AI directly on the edge.