---
title: Zeraix
emoji: ⚡
colorFrom: gray
colorTo: green
sdk: static
pinned: false
short_description: Imparo inference engine and Zeraix AI workspace
---

# Zeraix

**LLM inference that fits your hardware. AI tools built around your work.**

We build open-source software to make LLMs more useful on the hardware people already own — from the inference runtime to the everyday workspace.

[Website](https://www.zeraix.com) · [GitHub](https://github.com/zeraix) · [X / Twitter](https://twitter.com/ZeraixAI)

## Imparo — the inference engine

[Imparo](https://github.com/zeraix/imparo) is a hardware- and workload-adaptive LLM inference engine built in Rust.

- **Less execution overhead:** measured tuning and workload-aware execution, with Metal megakernel decode on supported paths.
- **Reusable context:** matching prefixes and shared paged state reduce repeated prefill work across conversations and agents.
- **Persistent state:** retained KV and recurrent state support resuming and branching long conversations and tool loops.
- **Measured improvements:** performance work is paired with output and state-transition checks.

Apple Silicon with Metal is the primary development and validation path. Other backend/model combinations remain qualification-specific. Context reuse does not imply concurrent decoding or continuous batching.

[Source & Quick Start](https://github.com/zeraix/imparo#quick-start) · [Performance](https://github.com/zeraix/imparo#performance) · [Contribute](https://github.com/zeraix/imparo#contributing)

## Zeraix — the AI workspace

[Zeraix](https://github.com/zeraix/zeraix) brings models, conversations, agents, files, and tools into an open-source desktop workspace, with local inference and optional cloud providers.

The desktop application and Imparo are separate projects. The current desktop release uses its documented llama.cpp-based runtimes; Imparo is not its default bundled engine.

[Download Zeraix](https://github.com/zeraix/zeraix/releases) · [Source & Docs](https://github.com/zeraix/zeraix)

## On Hugging Face

| Repository | Purpose |
| --- | --- |
| [imparo-benchmarks](https://huggingface.co/datasets/Zeraix/imparo-benchmarks) | Published inference benchmark results and measurement notes. |
| [llama-builds](https://huggingface.co/Zeraix/llama-builds) | Runtime and sandbox assets consumed by the Zeraix application. |
| [llama-seeds](https://huggingface.co/Zeraix/llama-seeds) | Version-matched prefix-cache seeds and auxiliary drafter assets for Zeraix. |

The two application asset repositories keep their existing download paths. They are not general-purpose standalone chat models or Imparo source mirrors.

## Recent updates

- **2026-09-10:** Imparo extended validation to Apple M4 Pro, reproducing optimization benefits demonstrated on M3 Pro. The published four-engine numerical table currently covers M3 Pro.
- **2026-09-09:** Zeraix 2.0 released.
- **2026-09-07:** Imparo published Metal megakernel decode and interleaved M3 Pro comparisons with llama.cpp, oMLX, and rapid-mlx.

## Build with us

We welcome contributions to model support, kernels, hardware validation, state management, benchmarks, integrations, and documentation. For performance changes, include a reproducible baseline and correctness checks.

[Imparo issues](https://github.com/zeraix/imparo/issues) · [Zeraix issues](https://github.com/zeraix/zeraix/issues) · [Contact](mailto:emma@zeraix.com)

Project source licenses and third-party artifact licenses are documented in their respective repositories. Model weights and upstream runtime components retain their own terms.