Integrations

The same optiq serve process exposes three API protocols on one port. Most coding agents and IDE plugins speak one of them, so you can run any of these tools against your local OptiQ-quantized model with a tiny config change.

The quickest way: optiq run

optiq run (mlx-optiq 0.5.9 or newer) does the setup for you. It starts optiq serve for the model (or reuses one already running on the port), waits until the server has generated a token, configures the agent for that session only, and launches it. No agent config file is edited, and a server it started is stopped when the agent exits.

$ optiq run claude   -m mlx-community/Qwen3.5-9B-OptiQ-4bit
$ optiq run codex    -m mlx-community/Qwen3.5-9B-OptiQ-4bit -- exec "fix the failing test"
$ optiq run          # lists the agents and which are installed

It also applies settings a local model needs and a hosted one doesn't: background model slots point at your model, tool search is off in Claude Code, and each agent is told your model's real context window so compaction happens in time. Each integration page below lists what it sets for that agent; the rest of this page covers wiring an agent to a server you run yourself.

Endpoints

optiq serve --model <path> --port 8080 exposes:

• /v1/chat/completions: OpenAI Chat Completions (default, used by most tools)
• /v1/messages: Anthropic Messages (set ANTHROPIC_BASE_URL)
• /v1/responses: OpenAI Responses (required by Codex; used by Cursor, Continue, Cline)

All three endpoints accept Bearer tokens that start with sk-optiq-. The suffix is anything you want; the prefix is checked. Authorization header may be omitted for local-dev curl calls.

Coverage matrix

"Verified version" is the build of each agent we ran the full wire test against on macOS (Apple Silicon). Newer versions should keep working; if you hit a regression please file an issue.

Quickstart (any tool)

# 1. Start the server (any OptiQ-quantized model)
$ optiq serve --model mlx-community/Qwen3.5-9B-OptiQ-4bit --port 8080

# 2. Hand the tool these settings:
#    Base URL:  http://localhost:8080/v1
#    API key:   sk-optiq-local  (any string prefixed sk-optiq-)
#    Protocol:  see "Coverage matrix" above for which endpoint the tool uses

MTP-aware serving

Add --mtp to enable in-checkpoint MTP speculative decoding for ~1.4-1.8× decode tok/s on Qwen3.5 / 3.6 family. Works transparently for all three endpoints; tools don't need to know about it.

$ optiq serve --model mlx-community/Qwen3.5-9B-OptiQ-4bit \
    --mtp --mtp-depth 2 --port 8080

What if my tool isn't listed?

If the tool can be pointed at a custom OpenAI-compatible base_url, it works with mlx-optiq out of the box. The matrix above just covers the tools we've tested end-to-end. Common candidates that work but aren't documented here yet:

• aider, set --openai-api-base http://localhost:8080/v1
• Open WebUI, add as an OpenAI-compatible connection in settings
• LangChain / LlamaIndex / DSPy, set the OpenAI client's base_url
• Anything using the openai Python SDK, instantiate with OpenAI(base_url=..., api_key="sk-optiq-...")