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

Zed's built-in agent runs inside the Zed editor (macOS, Linux, Windows) and can use local models from Ollama, LM Studio, llama.cpp or any OpenAI-compatible server. Zed discovers the models these servers expose. It suits developers who want an editor-native agent and have a model with reliable tool calling.

Source code Official docs Compare all agents

At a glance

Type: ide
Licence: Not verified
Latest release: Not verified
Status: Maintained
Local backends: ollama, lmstudio, llamacpp, openai-compatible
Needs native tool calling: Yes
MCP support: Not verified
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 (macOS (Homebrew)):
```
brew install --cask zed
```
Pull a coding model that supports tool calling (replace qwen3-coder:30b with your choice).
```
ollama pull qwen3-coder:30b
```
Make sure the Ollama server is running: open Ollama.app on macOS, or run it from a shell.
```
ollama serve
```
Raise the context Zed requests. Zed sends num_ctx to Ollama and defaults to 4096, so set it in Zed rather than in Ollama.
~/.config/zed/settings.json
```
{
  "language_models": {
    "ollama": {
      "context_window": 65536
    }
  }
}
```
In Zed, pick the Ollama model from the agent's model dropdown (or star icon, Configure, LLM Providers, Ollama, Connect).

Other ways to install

Linux

curl -f https://zed.dev/install.sh | sh

Windows (winget)

winget install -e --id ZedIndustries.Zed

Check that it works

Open the Agent Panel, choose the local model and ask it to read a file in your project. A tool call should appear in the thread, not just a text reply.

Which local models fit, by machine

Checked by this site's engine at the context Zed agent 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

Zed sends num_ctx 4096 to Ollama by default, whatever OLLAMA_CONTEXT_LENGTH says. Set context_window, or max_tokens per model.
If you turn auto_discover off and list models by hand, set "supports_tools": true on each one, or the agent cannot use tools with it.
llama.app's server listens on localhost:9931, while Zed's manual llama.cpp example uses http://localhost:8080. If no models appear, set language_models.llama.cpp.api_url to the port your server actually uses.
External agents connected through ACP (for example OpenHands or Claude Code) manage their own models; these settings only affect Zed's own agent.

Other coding agents

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

Sources (7), checked 2026-10-20