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

OpenCode is an open-source (MIT) coding agent that runs in the terminal, with a desktop app and IDE extension also available. It talks to Ollama, LM Studio and llama-server through an OpenAI-compatible provider entry in opencode.json, which suits people who want a full-featured terminal agent on local models.

Source code Official docs Compare all agents

At a glance

Type: cli
Licence: MIT
Latest release: 1.19.3 (2026-10-16)
Status: Maintained
Local backends: ollama, lmstudio, llamacpp, vllm, openai-compatible
Needs native tool calling: Yes
MCP support: Yes
Recommended minimum context: 16,000 tokens
Start-up prompt: ~7,000 tokens (single third-party measurement)
GitHub stars: 214.6k (2026-10-19)

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 (macOS / Linux):

curl -fsSL https://opencode.ai/install | bash

Start Ollama with a 64k context window (or set the context slider in the Ollama app's settings).
```
OLLAMA_CONTEXT_LENGTH=64000 ollama serve
```
In a second terminal, pull a tool-capable coding model (replace qwen3-coder:30b with any model you prefer).
```
ollama pull qwen3-coder:30b
```
Quickest path: let Ollama configure and launch OpenCode for you.
```
ollama launch opencode
```

Or add Ollama as a provider in your global OpenCode config (replace qwen3-coder:30b with the model you pulled).

~/.config/opencode/opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama (local)",
      "options": {
        "baseURL": "http://localhost:11434/v1"
      },
      "models": {
        "qwen3-coder:30b": {
          "name": "Qwen3-Coder 30B",
          "limit": {
            "context": 64000,
            "output": 8192
          }
        }
      }
    }
  }
}

Run OpenCode in your project and pick the model with /models.
```
opencode
```

Other ways to install

npm

npm install -g opencode-ai

Homebrew

brew install anomalyco/tap/opencode

Check that it works

List the models OpenCode can see from your local provider; your model should appear as provider/model. With Ollama, run `ollama ps` during a session and check the CONTEXT column.

opencode models ollama

Which local models fit, by machine

Checked by this site's engine at the context OpenCode 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

Ollama's OpenCode guide says OpenCode needs a 64k+ context window; OpenCode's own docs say to raise num_ctx (start around 16k-32k) if tool calls aren't working.
limit.context in opencode.json only tells OpenCode the window size. The OpenAI-compatible API cannot change Ollama's context, so set it on the server (OLLAMA_CONTEXT_LENGTH or the app slider).
`ollama launch opencode` uses an inline config and does not overwrite ~/.config/opencode/opencode.json; models defined only in opencode.json do not appear in its model picker.
OpenCode 2 is out and uses the same `opencode` command; these steps follow the OpenCode 1 docs, and the two cannot be installed side by side under the default command.

Other coding agents

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

Sources (9), checked 2026-10-20