Continue: discontinued. Last release, local setup and alternatives

Continue is a coding agent for VS Code and JetBrains, with a CLI (cn). It is no longer actively maintained: the repository is read-only, and the last extension release was 2.1.0 on Open VSX (19 June 2026). The final release still reads a config.yaml with Ollama, LM Studio and llama.cpp providers, but new users should pick a maintained agent.

Source code Official docs Compare all agents

At a glance

Type: vscode-extension, jetbrains, cli
Licence: Apache-2.0
Latest release: 2.1.0 (2026-06-19)
Status: Discontinued
Local backends: ollama, lmstudio, openai-compatible
Needs native tool calling: Partly (a fallback exists)
MCP support: Yes
Recommended minimum context: Not stated in its docs
Start-up prompt: Not measured
GitHub stars: 35.7k (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 (VS Code extension (final release)):
```
code --install-extension Continue.continue
```
Pull the model with the exact tag (replace qwen3-coder:30b with your choice).
```
ollama pull qwen3-coder:30b
```

Add it to your Continue config.yaml. Continue sends its own context length to Ollama, so set contextLength here; tool_use enables agent mode.

config.yaml

name: Local Config
version: 0.0.1
schema: v1
models:
  - name: Qwen3 Coder 30B
    provider: ollama
    model: qwen3-coder:30b
    roles:
      - chat
      - edit
      - apply
    capabilities:
      - tool_use
    defaultCompletionOptions:
      contextLength: 32768

Optionally pull a small model for autocomplete and add it with roles: [autocomplete].
```
ollama pull qwen2.5-coder:1.5b
```

Other ways to install

CLI (npm, final release)

npm i -g @continuedev/cli

Check that it works

Check that Ollama is up, then pick the model in Continue's model selector and send a message. "404 model not found" means the config tag does not match what ollama list shows.

curl http://localhost:11434

Which local models fit, by machine

Checked by this site's engine at the context Continue 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

No further fixes are coming: the repo is read-only and the maintainers say it is no longer actively maintained.
"Agent mode is not supported" means Continue does not think the model supports tools. Add capabilities: [tool_use]; if that fails, the model itself may not handle tools.
"Model requires more system memory" usually means Continue's default context length is larger than other tools'. Lower contextLength or use a smaller model.
Pull the exact tag the config names: a bare ollama pull deepseek-r1 fetches :latest, which may be a different size.

Other coding agents

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

Sources (12), checked 2026-10-20