Grux AI Download

Can I run Claude Code with a local model on my Mac?

Yes. Claude Code sends its requests to the address in the ANTHROPIC_BASE_URL environment variable, and three Mac runners now answer in Anthropic's Messages API format, so a model on your own machine can sit behind it. With Ollama, run ollama launch claude, or set the variable to your local Ollama address. With LM Studio 0.4.1 or newer, start its server and point the same variable at it. llama.cpp's server also serves /v1/messages, and tool use needs its jinja chat templates, on by default. What answers is then the model you loaded, not Claude, so the result is only as capable as that model: Ollama asks for a context window of 64k or more for local models, and LM Studio recommends at least 25K tokens. This page repeats each runner's own instructions and quotes no speed or quality figure, because we have not measured Claude Code on a local model.

Download Grux AI 3.3.1, free, for macOS 14 or later on Apple silicon.

Grux AI 3.3.1 · sources read 2026-11-18 · published 2026-11-19

The three setups

RunnerHow to point Claude Code at itWhat its documentation asks for
Ollamaollama launch claude, or the two variables belowA model that supports tools, with a context window of 64k or more for local models
LM Studiolms server start --port 1234, then the two variables belowVersion 0.4.1 or newer, for its Anthropic compatible endpoint; at least 25K tokens of context to start
llama.cppStart llama-server with a model; its server answers /v1/messagesTool use requires the --jinja option, which its README lists as enabled by default

Ollama and LM Studio both publish the same pair of variables. The key is a placeholder the runner ignores, and only the address changes.

# Ollama, default address
export ANTHROPIC_BASE_URL=http://localhost:11434
export ANTHROPIC_AUTH_TOKEN=ollama
claude --model qwen3-coder

# LM Studio, default address
export ANTHROPIC_BASE_URL=http://localhost:1234
export ANTHROPIC_AUTH_TOKEN=lmstudio
claude --model openai/gpt-oss-20b

Those model names are the ones each runner's own page uses in its example. After you set a variable, run /status inside Claude Code to see which address it is using; Ollama's page says Claude's settings files can override a shell variable.

What changes when the model is local

Which model to load

Pick the largest model your memory can hold with room for a long context. The which LLM can my Mac run page gives the sizing rule, best local LLM for coding on a Mac lists coding models by memory, and Ollama models scores the Ollama library.

Where Grux AI fits

Grux AI (MIT) does not need any of this to use a local model: it talks to Ollama directly, with no base address to set, and acts on your mail, calendar and files. The two also work together: Grux writes work orders for Claude Code when you want to change the app itself. See Claude Code Mac app for the official app and where Grux fits.

Where to check this

ClaimSource
Ollama connects Claude Code through its Messages API support; ollama launch claude; 64k or more context for local modelsOllama documentation, Claude Code
The two variables and the subset of the Messages API Ollama supportsOllama documentation, API compatibility
LM Studio 0.4.1 serves /v1/messages; the setup; at least 25K tokens of contextLM Studio blog, Use your LM Studio models in Claude Code
llama.cpp's server serves /v1/messages, and tool use requires --jinjallama.cpp server README
Claude Code sends requests to the address in ANTHROPIC_BASE_URLClaude Code documentation, LLM gateway

All five were read on 18 November 2026. These tools change quickly, so check the runner's page for the current model names before you copy a command.

Questions

Can Claude Code use a local model?
Yes. Ollama, LM Studio and llama.cpp each serve an Anthropic compatible endpoint, so you point Claude Code's ANTHROPIC_BASE_URL at your own machine and name a local model.
What is the easiest way to run Claude Code with Ollama?
Run ollama launch claude. Ollama's documentation describes it as launching Claude Code with Ollama, and asks for a context window of 64k or more for local models.
Does Claude Code with a local model still use Claude?
No. The model you loaded answers, so the quality is that model's. The agent is still Claude Code.
Do I need Claude Code to use Grux AI?
No. Grux AI runs on a local Ollama model by itself. Claude Code is only involved when you ask Grux to write a work order to change the app.
Download Grux AI 3.3.1 Read the source

Free, MIT licensed. macOS 14 or later, Apple silicon. 29.1 MB, signed and notarized by Apple. No account, no server, no subscription.