mlx-optiq
OptiQ Lab · local workbench

Your models, in the browser.

A local web app for the whole workflow: chat with your models, quantize new ones, fine-tune with your data, and compare them side by side. It runs on your Mac. No cloud, no account, no data leaving the machine.

$ optiq lab
localhost:8080 · OptiQ Lab
The workbench

Everything OptiQ does, with a UI.

The same MLX-native engine as the CLI, wrapped in a local web app. Pick a model from the Hub, chat with it, quantize your own, fine-tune on your data, and race two models head to head.

Chat

Chat with tools

Talk to any served model with sandboxed web search, Python, and terminal tools, plus image upload and chat-with-files retrieval with citations.

Arena

Model Arena

Run two models side by side on the same prompt and watch tokens per second and answers diverge in real time.

Hub

Model Hub

Browse the published OptiQ quants, search Hugging Face, and load a model with one click, straight into the Lab.

Quantize

Quantize wizard

Point it at any Hugging Face model and get a sensitivity-driven mixed-precision quant, with a live view of the per-layer bit allocation.

Fine-tune

SFT & DPO

Fine-tune with sensitivity-aware LoRA, SFT or DPO, on your own dataset, all local, with progress and loss curves in the browser.

Dataset

Dataset designer

Build and shape a training set from files and templates before you fine-tune, without leaving the app.

Under the hood The Lab drives the same optiq engine as the CLI, and serves models over the same dual-protocol server, so a model you serve in the Lab is the one OptiQ Code can drive. See the Lab docs.

A local AI workbench, one install away.

Run, quantize, fine-tune, and compare models on your own Mac.