rapid-mlx

library0.6.80pypypiunverified

Rapid-MLX provides AI inference on Apple Silicon with a drop-in OpenAI-compatible API. It claims 2-4x speedups over Ollama. Current version is 0.6.80, under active development with a weekly release cadence.

ai-ml devops

pip install rapid-mlx

github ↗homepage ↗

INSTALL

IMPORT

SIG · RAPID-MLX

rapid-mlx

ai-mlpythonv0.6.80

harness data pending

Install & Compatibility

Where this runs

No compatibility data collected yet for this library.

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

Model

✓ from vllm_mlx import Model

✗ from rapid_mlx import Model

Load a model and run a chat completion.

from rapid_mlx import Model model = Model('mlx-community/Mistral-7B-Instruct-v0.2-4bit') response = model.chat([{'role': 'user', 'content': 'Hello!'}]) print(response)

Debug

Known issues

gotchaOnly works on Apple Silicon (M1/M2/M3/M4). No CPU fallback.

fix

Check platform.machine() before installing.

affects: *

deprecatedThe old API `model.generate()` is deprecated in favor of `model.chat()`.

fix

Use model.chat() with OpenAI-style messages.

affects: <0.6.0

breakingVersion 0.6.0 changed all method signatures from positional args to keyword args.

fix

Update calls to use explicit parameter names.

affects: >=0.6.0

Upgrade

Version history

0.6.80latest on PyPI · released Jun 6, 2026

Audit

Dependencies

mlxrequiredRequired for Apple Silicon MLX backend

Agent activity

10 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/raullenchai/Rapid-MLX ↗

homepagehttps://github.com/raullenchai/Rapid-MLX ↗