---
title: "Local models"
canonical: "https://canmyagentuse.com/features/local-models"
contentKind: "feature"
locale: "en"
description: "Run against a model hosted on the operator's machine."
llmSummary: "Local model support lets a product use a model hosted on the operator's machine. Model servers, formats, authentication, and feature limitations are qualifiers."
publishedAt: "2026-08-28T00:00:00.000Z"
updatedAt: "2026-08-28T00:00:00.000Z"
verifiedAt: "2026-08-28"
tags: ["runtime"]
---

# Local models

Local model support lets a product use a model hosted on the operator's machine. Model servers, formats, authentication, and feature limitations are qualifiers.

- HTML: https://canmyagentuse.com/features/local-models
- JSON: https://canmyagentuse.com/api/v1/features/local-models.json
- Markdown: https://canmyagentuse.com/features/local-models.md

Terminology basis: **Common product term** — https://docs.ollama.com/quickstart.

## Current support at a glance

Local models: 5 supported, 0 partial, 0 unsupported, 26 unreviewed across 31 cataloged products.

- Reviewed current products: 5 of 31
- Supported: 5
- Partial: 0
- Unsupported: 0
- Unreviewed: 26
- Not applicable: 0

Unknown or unreviewed means insufficient published evidence; it does not mean unsupported.

This row asks whether the exact harness can send model requests to an operator-controlled local inference runtime. A cloud model with a desktop client is not a local model, and a configurable remote API base URL does not prove on-device execution.

Evidence should identify the supported runtimes or protocols, model-discovery behavior, tool-calling and multimodal constraints, authentication, and whether any prompts, telemetry, or embeddings still leave the device.

The matrix below lists published **web**, **desktop**, and **CLI** surfaces. Unreviewed cells remain **unknown** until a dated note and public source support a more specific status.

Use the Markdown and JSON twins if you are an agent reading this site.

## Catalog context

- Category: [models-context](/categories/models-context.md)
- Terminology basis: Common product term
- Aliases: self-hosted model, local inference, on-device model
- Family: [Models and context](/features/models-and-context.md)
- Siblings: [Automatic context compaction](/features/automatic-context-compaction.md), [Context compaction controls](/features/context-compaction-controls.md), [Context usage](/features/context-usage-visibility.md), [Context window](/features/context-window.md), [Model fallback](/features/model-fallback.md), [Model selection](/features/model-selection.md), [Output token limit](/features/output-token-limit.md), [Prompt cache controls](/features/prompt-cache-controls.md), [Prompt cache telemetry](/features/prompt-cache-telemetry.md), [Prompt caching](/features/prompt-cache-reuse.md), [Reasoning effort controls](/features/reasoning-effort-controls.md)

## Compatibility assertions

Unknown means insufficient published evidence; it does not mean unsupported.

### ChatGPT (web)

- Harness: [ChatGPT](/harnesses/chatgpt-web.md)
- current: **Unknown**
- preview: **Unknown**

### Claude (web)

- Harness: [Claude](/harnesses/claude-web.md)
- current: **Unknown**
- preview: **Unknown**

### Gemini (web)

- Harness: [Gemini](/harnesses/gemini-web.md)
- current: **Unknown**
- preview: **Unknown**

### Copilot (web)

- Harness: [Copilot](/harnesses/copilot-web.md)
- current: **Unknown**
- preview: **Unknown**

### Grok (web)

- Harness: [Grok](/harnesses/grok-web.md)
- current: **Unknown**
- preview: **Unknown**

### Grok Bot (desktop)

- Harness: [Grok Bot](/harnesses/grok-bot-desktop.md)
- current: **Unknown**

### Perplexity (web)

- Harness: [Perplexity](/harnesses/perplexity-web.md)
- current: **Unknown**
- preview: **Unknown**

### Le Chat (web)

- Harness: [Le Chat](/harnesses/le-chat.md)
- current: **Unknown**
- preview: **Unknown**

### Devin (web)

- Harness: [Devin](/harnesses/devin-web.md)
- current: **Unknown**
- preview: **Unknown**

### Replit Agent (web)

- Harness: [Replit Agent](/harnesses/replit-agent.md)
- current: **Unknown**
- preview: **Unknown**

### ChatGPT (desktop)

- Harness: [ChatGPT](/harnesses/chatgpt-desktop.md)
- current: **Unknown**
- preview: **Unknown**

### Claude (desktop)

- Harness: [Claude](/harnesses/claude-desktop.md)
- current: **Unknown**
- preview: **Unknown**

### Cursor (desktop)

- Harness: [Cursor](/harnesses/cursor.md)
- current: **Unknown**
- preview: **Unknown**

### OpenWork Desktop (desktop)

- Harness: [OpenWork Desktop](/harnesses/openwork-desktop.md)
- current: **Unknown**

### Copilot Chat (desktop)

- Harness: [Copilot Chat](/harnesses/vscode-copilot.md)
- current: **Supported**
  - Target: dated-documentation — current VS Code language-model documentation; observed 2026-08-28
  - Environment: preview-enabled
  - Constraint (experimental): using BYOK models in Agent Host sessions requires chat.agentHost.byokModels.enabled and an Agent Host restart
  - Constraint (runtime): local Ollama use now requires the official Ollama extension; some VS Code features such as semantic search and embeddings can still require a GitHub account or external service
  - Evidence: [Microsoft — AI language models in VS Code](https://code.visualstudio.com/docs/agent-customization/language-models) — documented; observed 2026-08-28
  - Qualification note 2: Evidence checked 2026-08-28: VS Code documents BYOK support for fully offline local models such as Ollama and an experimental setting that enables BYOK models in Agent Host sessions.
- preview: **Unknown**

### Chrome WebMCP origin trial (desktop)

- Harness: [Chrome WebMCP origin trial](/harnesses/chrome-webmcp-preview.md)
- current: **Unknown**

### Windsurf (desktop)

- Harness: [Windsurf](/harnesses/windsurf.md)
- current: **Unknown**
- preview: **Unknown**

### Zed Agent (desktop)

- Harness: [Zed Agent](/harnesses/zed-agent.md)
- current: **Unknown**
- preview: **Unknown**

### Continue (desktop)

- Harness: [Continue](/harnesses/continue.md)
- current: **Supported**
  - Target: dated-documentation — current Continue Ollama guide; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): local model quality and advertised tool calling determine whether Agent mode, edit, apply, embeddings, and other roles work reliably
  - Evidence: [Continue — Using Ollama with Continue](https://docs.continue.dev/guides/ollama-guide) — documented; observed 2026-08-28
  - Qualification note 3: Evidence checked 2026-08-28: Continue documents local Ollama configuration, automatic discovery of installed models, offline operation, and model-role limitations.
- preview: **Unknown**

### Cline (desktop)

- Harness: [Cline](/harnesses/cline.md)
- current: **Supported**
  - Target: dated-documentation — current Cline local-model guide; observed 2026-08-28
  - Environment: air-gapped
  - Constraint (runtime): requires a locally running Ollama or LM Studio endpoint and sufficient hardware; feature completeness depends on the model's tool-use behavior and context capacity
  - Evidence: [Cline — Local models overview](https://docs.cline.bot/running-models-locally/overview) — documented; observed 2026-08-28
  - Qualification note 5: Evidence checked 2026-08-28: Cline documents fully offline local-model operation with either Ollama or LM Studio and calls out hardware and tool-use constraints.
- preview: **Unknown**

### JetBrains AI (desktop)

- Harness: [JetBrains AI](/harnesses/jetbrains-ai.md)
- current: **Unknown**
- preview: **Unknown**

### Warp (desktop)

- Harness: [Warp](/harnesses/warp.md)
- current: **Unknown**
- preview: **Unknown**

### Claude CLI (cli)

- Harness: [Claude CLI](/harnesses/claude-cli.md)
- current: **Unknown**
- preview: **Unknown**

### ChatGPT CLI (cli)

- Harness: [ChatGPT CLI](/harnesses/chatgpt-cli.md)
- current: **Unknown**
- preview: **Unknown**

### Codex CLI (cli)

- Harness: [Codex CLI](/harnesses/codex-cli.md)
- current: **Unknown**
- preview: **Unknown**

### OpenCode (cli)

- Harness: [OpenCode](/harnesses/opencode.md)
- current: **Supported**
  - Target: dated-documentation — current OpenCode local-model documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): OpenCode can discover local Ollama models and configure local Ollama, vLLM, or OpenAI-compatible servers; declared capabilities and limits must match the actual model
  - Evidence: [OpenCode — Models](https://opencode.ai/v2/docs/models) — documented; observed 2026-08-28
  - Qualification note 6: Evidence checked 2026-08-28: OpenCode documents local Ollama discovery and explicit configuration for Ollama, vLLM, and other locally hosted OpenAI-compatible servers.
- preview: **Unknown**

### Gemini CLI (cli)

- Harness: [Gemini CLI](/harnesses/gemini-cli.md)
- current: **Unknown**
- preview: **Unknown**

### Aider (cli)

- Harness: [Aider](/harnesses/aider.md)
- current: **Supported**
  - Target: dated-documentation — current aider Ollama documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): weaker local models may fail aider's code-edit protocol; the documented default endpoint is the operator's local Ollama server
  - Evidence: [aider — Ollama](https://aider.chat/docs/llms/ollama.html) — documented; observed 2026-08-28
  - Qualification note 4: Evidence checked 2026-08-28: aider documents connecting directly to a local Ollama endpoint and selecting local models from the CLI.
- preview: **Unknown**

### Goose (cli)

- Harness: [Goose](/harnesses/goose.md)
- current: **Unknown**
- preview: **Unknown**

### Copilot CLI (cli)

- Harness: [Copilot CLI](/harnesses/copilot-cli.md)
- current: **Unknown**
- preview: **Unknown**

### Amp (cli)

- Harness: [Amp](/harnesses/amp-cli.md)
- current: **Unknown**
- preview: **Unknown**