Goose with a local model: setup for Ollama, LM Studio or llama.cpp

goose is a general-purpose open-source agent with a desktop app (macOS, Linux, Windows) and a CLI; coding is one use among many, and tools come from MCP extensions. It has built-in Ollama and LM Studio providers and can reach other local servers through its OpenAI provider. It suits people who want one agent for coding and non-coding tasks, with a model that handles tool calling well.

Source code Official docs Compare all agents

At a glance

Type: cli, desktop
Licence: Not verified
Latest release: Not verified
Status: Maintained
Local backends: ollama, ramalama, docker-model-runner, openai-compatible
Needs native tool calling: Yes
MCP support: Yes
Recommended minimum context: Not stated in its docs
Start-up prompt: Not measured
GitHub stars: Not verified

How to set it up with a local model

Pick your backend. Each command has its own Copy button. Where a step uses an example model, swap in the one you run; the table below lists the ones that fit your machine.

Install it (CLI (macOS / Linux)):

curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash

Pull a model that supports tool calling (replace qwen3-coder:30b with your choice).
```
ollama pull qwen3-coder:30b
```
Raise Ollama's context window (goose's docs say the 4096-token default is too low for extensions; Ollama's docs ask for at least 64K for agents); or set the context slider in the Ollama app's Settings instead.
```
OLLAMA_CONTEXT_LENGTH=64000 ollama serve
```
Run the goose configurator and choose Configure Providers, then Ollama.
```
goose configure
```
Accept the host http://localhost:11434 and enter the model name you pulled.
```
qwen3-coder:30b
```
In goose Desktop instead: Settings, Configure Provider, Ollama, Configure; confirm API Host is http://localhost:11434 and Submit.

Other ways to install

CLI (Homebrew)

brew install block-goose-cli

Desktop (Homebrew, macOS)

brew install --cask block-goose

Check that it works

Start a session and ask goose to list the files in the current directory; it should call its developer extension rather than only reply in text.

goose session

Which local models fit, by machine

Checked by this site's engine at the context Goose needs, with 32 GB of system RAM for MoE offload. A Mac counts three quarters of unified memory as usable.

Machine	Model	Quant	Context	Fit	Ollama
12 GB GPU	Qwen 3.5 9B	Q4_K_M	32,768	Comfortable (7.4 GB of 12 GB)	`qwen3.5:9b`
	Qwen 3.6 35B-A3B	Q4_K_M	32,768	With CPU offload (MoE) (22.7 GB of 12 GB)	`qwen3.6:35b-a3b`
16 GB GPU	Qwen 3.5 9B	Q4_K_M	32,768	Comfortable (7.4 GB of 16 GB)	`qwen3.5:9b`
	Qwen 3.6 35B-A3B	Q4_K_M	32,768	With CPU offload (MoE) (22.7 GB of 16 GB)	`qwen3.6:35b-a3b`
24 GB GPU	Qwen3.8 27B	Q4_K_M	32,768	Comfortable (19.9 GB of 24 GB)	`qwen3.8:27b`
	Qwen 3.6 27B	Q4_K_M	32,768	Comfortable (19.9 GB of 24 GB)	`qwen3.6:27b`
	Devstral Small 2 24B	Q4_K_M	32,768	Comfortable (20.7 GB of 24 GB)	`devstral-small-2:24b`
	Qwen 3.6 35B-A3B	Q4_K_M	65,536	Tight (23.3 GB of 24 GB)	`qwen3.6:35b-a3b`
32 GB GPU	Qwen3.8 27B	Q4_K_M	32,768	Comfortable (19.9 GB of 32 GB)	`qwen3.8:27b`
	Qwen 3.6 27B	Q4_K_M	32,768	Comfortable (19.9 GB of 32 GB)	`qwen3.6:27b`
	Devstral Small 2 24B	Q4_K_M	32,768	Comfortable (20.7 GB of 32 GB)	`devstral-small-2:24b`
	Qwen 3.6 35B-A3B	Q4_K_M	65,536	Comfortable (23.3 GB of 32 GB)	`qwen3.6:35b-a3b`
	Qwen3-Coder 30B-A3B (MoE)	Q4_K_M	65,536	Comfortable (25.7 GB of 32 GB)	`qwen3-coder:30b`
Mac, 64 GB	Qwen 3.6 35B-A3B	Q8_0	131,072	Comfortable (40.7 GB of 48 GB)	—

Your exact machine: filter the matrix or check any model in the analyzer.

Common problems with local models

goose relies on tool calling. A model without it can only chat, and you must disable all extensions to use it.
If goose ignores extensions or .goosehints, the context is too short: raise OLLAMA_CONTEXT_LENGTH (goose docs name the 4096 default as the usual cause).
Plain deepseek-r1 on Ollama has no tool calling; goose's docs point to a community build (michaelneale/deepseek-r1-goose) instead.
The project moved from block/goose to aaif-goose/goose and its docs to goose-docs.ai; older install links may 404.

Other coding agents

How they rank for local models: the best agent harness for local LLMs.

Sources (9), checked 2026-10-20