AX Engine

High-performance local inference engine for Apple Silicon — Python bindings.

Installation

Python SDK (pip)

Use pip when your application imports ax_engine or needs AX Engine's optional Python integrations. Install the wheel in a virtual environment:

python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install --upgrade pip
python3 -m pip install --upgrade "ax-engine[download]>=6.12.1,<7"
ax-engine doctor

Requires macOS 26+, Apple Silicon (M2 Max or newer), Python 3.10+. The current macOS arm64 wheel also includes the ax-engine orchestration CLI plus bundled ax-engine-server and ax-engine-bench binaries when you need a wheel-only install.

Verify the installed command surface:

ax-engine doctor
ax-engine-server --help

Native CLI and server (Homebrew, primary)

For end users running the TUI, CLI, server, or benchmark tools, Homebrew is the primary installation channel:

brew tap defai-digital/ax-engine
brew trust --formula \
  defai-digital/ax-engine/ax-engine \
  defai-digital/ax-engine/mlx \
  defai-digital/ax-engine/mlx-c
brew install defai-digital/ax-engine/ax-engine
ax-engine doctor

If both channels are installed, an active virtual environment normally shadows Homebrew's commands. Use which -a ax-engine to identify every copy and avoid mixing versions in one shell. See the Getting Started installation guide for requirements, linkage details, and troubleshooting.

Quick start

import ax_engine

session = ax_engine.Session(mlx=True, mlx_model_artifacts_dir="/path/to/model")
result = session.generate([token_id, ...], max_output_tokens=128)
print(result.output_tokens)

Native Unlimited-OCR image requests

AX Engine 6.12 exposes native Unlimited-OCR global and high-resolution tile paths without model repository code. Tokenize a prompt containing exactly one literal <image>, then let the helper expand and attach one local path or Pillow image:

from tokenizers import Tokenizer
import ax_engine

model_dir = "/path/to/ax-unlimited-ocr"
tokenizer = Tokenizer.from_file(f"{model_dir}/tokenizer.json")
input_tokens = tokenizer.encode(
    "<image>Convert the document to markdown.",
    add_special_tokens=False,
).ids
request = ax_engine.prepare_unlimited_ocr_image_request(
    model_dir,
    [0, *input_tokens],
    ["page.png"],
)

with ax_engine.Session(
    model_id="unlimited_ocr",
    mlx=True,
    mlx_model_artifacts_dir=model_dir,
) as session:
    result = session.generate(
        request.input_tokens,
        multimodal_inputs=request.multimodal_inputs,
        max_output_tokens=8192,
        no_repeat_ngram_size=35,
        ngram_window=128,
    )

text = tokenizer.decode(result.output_tokens, skip_special_tokens=False)

The public path accepts exactly one bounded RGB source image. By default it selects the released processor's bounded 640px tile grid (up to 32 tiles) in addition to the 1024px global view; pass cropping=False only for an explicit global-only tradeoff. Resize, tiling, letterboxing, normalization, dual-vision projection, and BF16 conversion run in the native MLX implementation.

Or use the OpenAI-compatible shim:

python -m ax_engine.openai_server \
    --model-id my-model \
    --mlx-model-artifacts-dir /path/to/model \
    --tokenizer /path/to/tokenizer.json \
    --port 31418

Then point any OpenAI client at http://127.0.0.1:31418.

Optional dependencies

Install the OpenAI shim or image/audio helpers with the matching extra:

python3 -m pip install --upgrade "ax-engine[openai]>=6.12.1,<7"
python3 -m pip install --upgrade "ax-engine[multimodal]>=6.12.1,<7"

Requirements

macOS 26 (Tahoe) or later
Apple Silicon — M2 Max / M2 Ultra / M3 / M4 family (32 GB RAM minimum)
Python 3.10+

Project

github.com/defai-digital/ax-engine

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

ax_engine-6.12.1-cp310-abi3-macosx_26_0_arm64.whl (71.6 MB view details)

Uploaded Aug 2, 2026 CPython 3.10+macOS 26.0+ ARM64

File details

Details for the file ax_engine-6.12.1-cp310-abi3-macosx_26_0_arm64.whl.

File metadata

Download URL: ax_engine-6.12.1-cp310-abi3-macosx_26_0_arm64.whl
Upload date: Aug 2, 2026
Size: 71.6 MB
Tags: CPython 3.10+, macOS 26.0+ ARM64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for ax_engine-6.12.1-cp310-abi3-macosx_26_0_arm64.whl
Algorithm	Hash digest
SHA256	`2330a06be6759bf71de86752e01690a6c0b0872935f7603922dcd097e05afab7`
MD5	`dcfbbf4a118c61ff3626932ced145706`
BLAKE2b-256	`3540634024a8b983ceacb1b7275f3eb68bdf69dbc4ee9b1148680d3e119e3b95`

See more details on using hashes here.

Provenance

The following attestation bundles were made for ax_engine-6.12.1-cp310-abi3-macosx_26_0_arm64.whl:

Publisher: pypi.yml on defai-digital/ax-engine

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: ax_engine-6.12.1-cp310-abi3-macosx_26_0_arm64.whl
- Subject digest: 2330a06be6759bf71de86752e01690a6c0b0872935f7603922dcd097e05afab7
- Sigstore transparency entry: 2329038276
- Sigstore integration time: Aug 2, 2026
Source repository:
- Permalink: defai-digital/ax-engine@c71ef2f354787db17304d9e0d62b4c9485d284ca
- Branch / Tag: refs/tags/v6.12.1
- Owner: https://github.com/defai-digital
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: pypi.yml@c71ef2f354787db17304d9e0d62b4c9485d284ca
- Trigger Event: push