Which coding agent harness works with your local model?

Setups that fit (24–32 GB class)

Ordered by our reading: most memory headroom first, then the smaller system prompt, then pairings the harness’s own docs name. Not a quality benchmark.

• Pi coding agentcliMCP

  Pi is a minimal, extensible open-source (MIT) coding agent for the terminal, with four core tools (read, write, edit, bash) and a very short system prompt. It has a built-in llama.cpp router integration and connects to Ollama, LM Studio and other OpenAI-compatible servers through ~/.pi/agent/models.json, which suits people who want a small prompt on a tight context budget.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Pi coding agent with a local model ▾

  OllamaLM Studiollama.cpp

  1. Install it (macOS / Linux):

     curl -fsSL https://pi.dev/install.sh | sh

     Copy

  2. Start Ollama with a 64k context window (or set the context slider in the Ollama app's settings).

     OLLAMA_CONTEXT_LENGTH=64000 ollama serve

     Copy

  3. In a second terminal, pull a tool-capable coding model (replace qwen3-coder:30b with any model you prefer).

     ollama pull qwen3-coder:30b

     Copy

  4. Quickest path: let Ollama install Pi if needed, configure it and start a session.

     ollama launch pi

     Copy

  5. Or add Ollama to Pi's models file yourself (the dummy key makes the model available; Ollama ignores it).

     ~/.pi/agent/models.json

     {
       "$schema": "https://pi.dev/schemas/models.schema.json",
       "providers": {
         "ollama": {
           "baseUrl": "http://localhost:11434/v1",
           "api": "openai-completions",
           "apiKey": "ollama",
           "models": [
             {
               "id": "qwen3-coder:30b"
             }
           ]
         }
       }
     }

     Copy

  6. Make it the default provider and model.

     ~/.pi/agent/settings.json

     {
       "defaultProvider": "ollama",
       "defaultModel": "qwen3-coder:30b"
     }

     Copy

  Other ways to install

  npm (Node.js 22.19+)

  npm install -g --ignore-scripts @earendil-works/pi-coding-agent

  Copy

  Full Pi coding agent setup guide, with troubleshooting →

• OpenCodecliMCP

  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.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up OpenCode with a local model ▾

  OllamaLM Studiollama.cpp

  1. Install it (macOS / Linux):

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

     Copy

  2. Start Ollama with a 64k context window (or set the context slider in the Ollama app's settings).

     OLLAMA_CONTEXT_LENGTH=64000 ollama serve

     Copy

  3. In a second terminal, pull a tool-capable coding model (replace qwen3-coder:30b with any model you prefer).

     ollama pull qwen3-coder:30b

     Copy

  4. Quickest path: let Ollama configure and launch OpenCode for you.

     ollama launch opencode

     Copy

  5. 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
               }
             }
           }
         }
       }
     }

     Copy

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

     opencode

     Copy

  Other ways to install

  npm

  npm install -g opencode-ai

  Copy

  Homebrew

  brew install anomalyco/tap/opencode

  Copy

  Full OpenCode setup guide, with troubleshooting →

• Qwen CodecliMCP

  Qwen Code is Alibaba's open-source (Apache-2.0) terminal coding agent, with VS Code, Zed and JetBrains integrations and an experimental web UI. Its docs show local servers such as Ollama and LM Studio configured as OpenAI-compatible providers in ~/.qwen/settings.json, which suits people already running Qwen-family models locally.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)Named in its docs

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Qwen Code with a local model ▾

  OllamaLM Studiollama.cpp

  1. Install it (macOS / Linux):

     curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.sh | bash

     Copy

  2. Start Ollama with a 64k context window (or set the context slider in the Ollama app's settings).

     OLLAMA_CONTEXT_LENGTH=64000 ollama serve

     Copy

  3. In a second terminal, pull a tool-capable coding model (replace qwen3-coder:30b with any model you prefer).

     ollama pull qwen3-coder:30b

     Copy

  4. Add Ollama as an OpenAI-compatible provider in your user settings (replace qwen3-coder:30b with the model you pulled; the key is a placeholder Ollama ignores).

     ~/.qwen/settings.json

     {
       "env": {
         "OLLAMA_API_KEY": "ollama"
       },
       "modelProviders": {
         "openai": [
           {
             "id": "qwen3-coder:30b",
             "envKey": "OLLAMA_API_KEY",
             "baseUrl": "http://localhost:11434/v1",
             "generationConfig": {
               "contextWindowSize": 64000
             }
           }
         ]
       },
       "security": {
         "auth": {
           "selectedType": "openai"
         }
       },
       "model": {
         "name": "qwen3-coder:30b"
       }
     }

     Copy

  5. Start Qwen Code in your project; switch models later with /model.

     qwen

     Copy

  Other ways to install

  npm (Node.js 22+)

  npm install -g @qwen-code/qwen-code@latest

  Copy

  Homebrew

  brew install qwen-code

  Copy

  Full Qwen Code setup guide, with troubleshooting →

• Clinevscode-extension+cliMCP

  Cline is an open-source (Apache-2.0) coding agent that runs as an extension in VS Code, Cursor, Windsurf and JetBrains IDEs, with a separate terminal CLI. It has built-in Ollama and LM Studio providers and a Compact Prompt option for local inference, which suits people who want an agent inside their editor.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Cline with a local model ▾

  OllamaLM Studiollama.cpp

  1. Install it in VS Code: Extensions view → search "Cline" → Install.

  2. Start Ollama with a 32k context window (or set the context slider in the Ollama app's settings).

     OLLAMA_CONTEXT_LENGTH=32768 ollama serve

     Copy

  3. In a second terminal, pull a tool-capable coding model (replace qwen3-coder:30b with any model you prefer).

     ollama pull qwen3-coder:30b

     Copy

  4. In Cline Settings, set API Provider to Ollama and Base URL to http://localhost:11434.

  5. Select your model from the dropdown, or type it (e.g. qwen3-coder:30b).

  6. Set Context Window to at least 32K tokens in the same settings panel.

  7. Enable Use Compact Prompt under Settings → Features.

  Other ways to install

  JetBrains: Settings → Plugins → Marketplace → search "Cline" → Install

  CLI (npm, Node.js 20+)

  npm install -g cline

  Copy

  Full Cline setup guide, with troubleshooting →

• Kilo Codevscode-extension+jetbrains+cliMCP

  Kilo Code is an open-source (MIT) coding agent for VS Code, JetBrains and the terminal; the Kilo CLI is a fork of OpenCode. It has Ollama and LM Studio providers configured in the settings UI or kilo.json, and its docs suggest a 24 GB+ GPU or a 32 GB+ Mac for local models.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Kilo Code with a local model ▾

  OllamaLM Studio

  1. Install it in VS Code: Extensions view → search "Kilo Code" → Install.

  2. Start Ollama with a 32k context window (or set the context slider in the Ollama app's settings).

     OLLAMA_CONTEXT_LENGTH=32768 ollama serve

     Copy

  3. In a second terminal, pull Kilo's recommended model (replace it with any tool-capable model you prefer).

     ollama pull qwen3-coder:30b

     Copy

  4. In the extension, open Settings → Providers and add Ollama (no API key needed).

  5. Set "Context Window Size (num_ctx)" to at least 32k in the provider settings.

  6. For the CLI (or a model missing from the picker), register the model in kilo.json with tool calling and its context limit.

     ~/.config/kilo/kilo.json

     {
       "model": "ollama/qwen3-coder:30b",
       "provider": {
         "ollama": {
           "models": {
             "qwen3-coder:30b": {
               "name": "Qwen3-Coder 30B",
               "tool_call": true,
               "limit": {
                 "context": 32768,
                 "output": 8192
               }
             }
           }
         }
       }
     }

     Copy

  Other ways to install

  JetBrains: Settings → Plugins → search "Kilo Code" → Install

  CLI (npm)

  npm install -g @kilocode/cli

  Copy

  CLI (macOS / Linux)

  curl -fsSL https://kilo.ai/cli/install | bash

  Copy

  Full Kilo Code setup guide, with troubleshooting →

• Crush (Charm)cliMCP

  Crush is Charm's terminal coding agent, with LSP integration and MCP support. It is configured with a crushrc file (Bash with Crush builtins) and auto-discovers models from Ollama, LM Studio and llama.cpp when you add them as providers. It suits terminal users who want a local model without writing a JSON provider config.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Crush with a local model ▾

  OllamaLM Studiollama.cpp

  1. Install it (Homebrew):

     brew install charmbracelet/tap/crush

     Copy

  2. Pull a coding model that supports tool calling (replace qwen3-coder:30b with your choice).

     ollama pull qwen3-coder:30b

     Copy

  3. Raise Ollama's context window (Ollama's docs ask for at least 64K for coding agents); or set the context slider in the Ollama app's Settings instead.

     OLLAMA_CONTEXT_LENGTH=64000 ollama serve

     Copy

  4. Add Ollama as a provider in your crushrc; with no model list, Crush discovers your pulled models.

     ~/.config/crush/crushrc

     provider add ollama \
       --name Ollama \
       --type ollama \
       --base-url "http://localhost:11434/v1/"

     Copy

  5. Optionally pin the model and tell Crush its context window (match the value Ollama serves).

     ~/.config/crush/crushrc

     model add ollama/qwen3-coder:30b \
       --name "Qwen3 Coder 30B" \
       --context-window 64000

     Copy

  6. Run crush in your project and pick the Ollama model.

     crush

     Copy

  Other ways to install

  npm

  npm install -g @charmland/crush

  Copy

  Windows (winget)

  winget install charmbracelet.crush

  Copy

  Go

  go install github.com/charmbracelet/crush@latest

  Copy

  Full Crush setup guide, with troubleshooting →

• OpenHandsweb-ui+cli

  OpenHands is an open-source (MIT) coding agent with a web GUI that runs in Docker, plus a CLI. Its local-model guide connects it to LM Studio, Ollama, vLLM or SGLang through an OpenAI-compatible base URL. It suits users with at least a 24 GB GPU or a 64 GB Apple Silicon Mac, which is what the docs ask for to run their recommended Qwen3.6-35B-A3B.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)Named in its docs

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up OpenHands with a local model ▾

  OllamaLM Studio

  1. Install it (Web GUI (Docker, as in the local-LLM guide)):

     docker run -it --rm --pull=always \
         -e AGENT_SERVER_IMAGE_REPOSITORY=ghcr.io/openhands/agent-server \
         -e AGENT_SERVER_IMAGE_TAG=1.26.0-python \
         -e LOG_ALL_EVENTS=true \
         -v /var/run/docker.sock:/var/run/docker.sock \
         -v ~/.openhands:/.openhands \
         -p 3000:3000 \
         --add-host host.docker.internal:host-gateway \
         --name openhands-app \
         docker.openhands.dev/openhands/openhands:1.8

     Copy

  2. Start Ollama with at least 22K context (32K here), listening on all interfaces so the Docker container can reach it, then pull the model (replace qwen3.6:35b-a3b if you want another).

     OLLAMA_CONTEXT_LENGTH=32768 OLLAMA_HOST=0.0.0.0:11434 OLLAMA_KEEP_ALIVE=-1 nohup ollama serve &
     ollama pull qwen3.6:35b-a3b

     Copy

  3. Start the OpenHands web GUI with the Docker command above and open http://localhost:3000.

  4. In Settings, open the LLM tab, click "see advanced settings" and turn on the Advanced toggle.

  5. Set the custom model (openai/ plus the Ollama tag), the base URL and any placeholder API key, then Save Settings.

     Custom Model: openai/qwen3.6:35b-a3b
     Base URL:     http://host.docker.internal:11434/v1
     API Key:      local-llm

     Copy

  Other ways to install

  CLI (uv)

  uv tool install openhands --python 3.12

  Copy

  CLI (binary)

  curl -fsSL https://install.openhands.dev/install.sh | sh

  Copy

  Full OpenHands setup guide, with troubleshooting →

• AidercliNo release since 2026-02-12

  Aider is an open-source (Apache-2.0) AI pair-programming tool for the terminal that edits files with text edit formats rather than native tool calls. It works with Ollama, LM Studio and any OpenAI-compatible server; development has slowed, with the last PyPI release (0.86.2) on 2026-02-12.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Aider with a local model ▾

  OllamaLM Studiollama.cpp

  1. Install it (macOS / Linux):

     curl -LsSf https://aider.chat/install.sh | sh

     Copy

  2. Point aider at your Ollama server.

     export OLLAMA_API_BASE=http://127.0.0.1:11434

     Copy

  3. Pull a model (replace qwen3-coder:30b with any model you prefer).

     ollama pull qwen3-coder:30b

     Copy

  4. Start Ollama; aider's docs use an 8k default context here because aider sizes num_ctx per request itself.

     OLLAMA_CONTEXT_LENGTH=8192 ollama serve

     Copy

  5. In another terminal, run aider from your project with the ollama_chat/ prefix.

     aider --model ollama_chat/qwen3-coder:30b

     Copy

  6. Optional: pin a fixed context window instead of aider's per-request sizing.

     .aider.model.settings.yml

     - name: ollama_chat/qwen3-coder:30b
       extra_params:
         num_ctx: 65536

     Copy

  Other ways to install

  pip

  python -m pip install aider-install && aider-install

  Copy

  uv

  uv tool install --force --python python3.12 --with pip aider-chat@latest

  Copy

  Full Aider setup guide, with troubleshooting →

• Goosecli+desktopMCP

  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.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Goose with a local model ▾

  OllamaLM Studiollama.cpp

  1. Install it (CLI (macOS / Linux)):

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

     Copy

  2. Pull a model that supports tool calling (replace qwen3-coder:30b with your choice).

     ollama pull qwen3-coder:30b

     Copy

  3. 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

     Copy

  4. Run the goose configurator and choose Configure Providers, then Ollama.

     goose configure

     Copy

  5. Accept the host http://localhost:11434 and enter the model name you pulled.

     qwen3-coder:30b

     Copy

  6. 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

  Copy

  Desktop (Homebrew, macOS)

  brew install --cask block-goose

  Copy

  Full Goose setup guide, with troubleshooting →

• Zed agentide

  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.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Zed agent with a local model ▾

  OllamaLM Studiollama.cpp

  1. Install it (macOS (Homebrew)):

     brew install --cask zed

     Copy

  2. Pull a coding model that supports tool calling (replace qwen3-coder:30b with your choice).

     ollama pull qwen3-coder:30b

     Copy

  3. Make sure the Ollama server is running: open Ollama.app on macOS, or run it from a shell.

     ollama serve

     Copy

  4. 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
         }
       }
     }

     Copy

  5. 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

  Copy

  Windows (winget)

  winget install -e --id ZedIndustries.Zed

  Copy

  Full Zed agent setup guide, with troubleshooting →

• GitHub Copilot BYOK (VS Code)vscode-chat

  Bring Your Own Key (BYOK) in VS Code lets the built-in chat and agent use models you supply, including local ones, without a Copilot plan or GitHub sign-in. Ollama is connected through the official Ollama extension, and other local servers through the Custom Endpoint provider. It suits VS Code users who want to keep the native chat UI; inline suggestions, semantic search and embeddings still need GitHub's service.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (19.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Devstral Small 2 24B · Q4_K_M · set context to at least 32,768 tokens · Comfortable (20.7 GB of 24 GB usable)

    ollama pull devstral-small-2:24b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up GitHub Copilot BYOK with a local model ▾

  OllamaLM Studiollama.cpp

  1. Install it (Ollama extension (VS Code CLI)):

     code --install-extension Ollama.ollama

     Copy

  2. Install the official Ollama extension. The built-in Ollama provider in VS Code is deprecated.

     code --install-extension Ollama.ollama

     Copy

  3. Pull a model that supports tool calling (replace qwen3-coder:30b with your choice).

     ollama pull qwen3-coder:30b

     Copy

  4. Raise Ollama's context window (the Ollama VS Code guide asks for at least 64K); or set the context slider in the Ollama app's Settings instead.

     OLLAMA_CONTEXT_LENGTH=65536 ollama serve

     Copy

  5. Reload the VS Code window, open Chat and choose the model from the Ollama section of the model picker.

  Full GitHub Copilot BYOK setup guide, with troubleshooting →

• Codex CLI (--oss)cli

  Codex CLI is OpenAI's open-source (Apache-2.0) terminal coding agent. Its --oss mode runs against a local Ollama or LM Studio server, and Ollama can launch it with a ready-made profile; it suits people who want OpenAI's agent loop on a machine that can hold a 64k context.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 64,000 tokens · Tight (21.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 64,000 tokens · Tight (21.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)Named in its docs

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Codex CLI with a local model ▾

  OllamaLM Studio

  1. Install it (macOS / Linux):

     curl -fsSL https://chatgpt.com/codex/install.sh | sh

     Copy

  2. Start Ollama with a 64k context window (or set the context slider in the Ollama app's settings).

     OLLAMA_CONTEXT_LENGTH=64000 ollama serve

     Copy

  3. In a second terminal, pull a tool-capable coding model (replace qwen3-coder:30b with any model you prefer).

     ollama pull qwen3-coder:30b

     Copy

  4. Quickest path: let Ollama launch Codex with a dedicated profile; /model inside Codex switches between your installed tool-capable models.

     ollama launch codex

     Copy

  5. Or run Codex in OSS mode against Ollama with a specific model.

     codex --oss -m qwen3-coder:30b

     Copy

  6. Optionally make Ollama the default local provider for --oss.

     ~/.codex/config.toml

     oss_provider = "ollama"

     Copy

  Other ways to install

  npm

  npm install -g @openai/codex

  Copy

  Homebrew

  brew install --cask codex

  Copy

  Full Codex CLI setup guide, with troubleshooting →

• Claude Code (local backend)cliMCP

  Claude Code is Anthropic's proprietary terminal coding agent; pointed at a local server's Anthropic-compatible API, it runs against open-weight models. Ollama and LM Studio both document this setup, and it suits people already using Claude Code who have the memory for a 64k+ context.

  Models that fit your machine

  • Qwen3.8 27B · Q4_K_M · set context to at least 64,000 tokens · Tight (21.9 GB of 24 GB usable)

    ollama pull qwen3.8:27b

    Copy
  • Qwen 3.6 27B · Q4_K_M · set context to at least 64,000 tokens · Tight (21.9 GB of 24 GB usable)

    ollama pull qwen3.6:27b

    Copy
  • Qwen 3.6 35B-A3B · Q4_K_M · set context to at least 65,536 tokens · Tight (23.3 GB of 24 GB usable)Named in its docs

    ollama pull qwen3.6:35b-a3b

    Copy
  How to set up Claude Code with a local model ▾

  OllamaLM Studio

  1. Install it (macOS / Linux):

     curl -fsSL https://claude.ai/install.sh | bash

     Copy

  2. Start Ollama with a 64k context window (or set the context slider in the Ollama app's settings).

     OLLAMA_CONTEXT_LENGTH=64000 ollama serve

     Copy

  3. In a second terminal, pull a tool-capable coding model (replace qwen3-coder:30b with any model you prefer).

     ollama pull qwen3-coder:30b

     Copy

  4. Quickest path: let Ollama configure and launch Claude Code.

     ollama launch claude

     Copy

  5. Or point Claude Code at Ollama's Anthropic-compatible API yourself.

     export ANTHROPIC_AUTH_TOKEN=ollama
     export ANTHROPIC_API_KEY=""
     export ANTHROPIC_BASE_URL=http://localhost:11434

     Copy

  6. Tell Claude Code the real context window, since it assumes 200K for model IDs it doesn't recognize.

     export CLAUDE_CODE_MAX_CONTEXT_TOKENS=64000

     Copy

  7. Run Claude Code with your local model.

     claude --model qwen3-coder:30b

     Copy

  Other ways to install

  Windows (PowerShell)

  irm https://claude.ai/install.ps1 | iex

  Copy

  Full Claude Code setup guide, with troubleshooting →

All 16 harnesses compared

Click a column name to sort. Stars and versions carry their checked date on hover; system prompt sizes are community-measured.