Run LLMs Locally to Replace ChatGPT Plus
Serve a capable open model locally with Ollama and drop the ChatGPT Plus subscription.
Run this workflow
See exactly what it produces before you build it.
Build this with your agent
One copy-paste hands Claude Code, Codex, or Cursor the full recipe, steps included, nothing to fetch.
Intended Use
Anyone wanting daily ChatGPT-style usage without the $20/mo subscription, willing to run a local model on their own hardware.
Not for
- Cutting-edge reasoning that needs the very latest frontier model
- Devices with <8GB unified memory
Replaces ChatGPT Plus
The Stack
Tested Against
ollama@0.5deepseek-v4Side effects & data flow
- Network
- ollama.com
- Writes
- ~/.ollama/
- Credentials
- none required
Steps
- 1
Install and pull a model
Install Ollama and pull an open-weight model.
curl -fsSL https://ollama.com/install.sh | sh && ollama pull deepseek-v4 - 2
Smoke-test the model
Send a quick prompt to confirm everything's wired up.
ollama run deepseek-v4 "Say hello in 3 words"
Eval, 1 fixture
Last passed: verified 1mo agosmoke-promptrubrictimeout 60s · max $0.02Judge: claude-sonnet-4-5 Rubric: Pass if the response is 1-10 words long and reads as a greeting (not an error message).
Results
Saves $20/month; no rate limits, full privacy.
Did this work for you?
Our CI checks the setup runs. You tell us if the whole thing worked. Tell us straight.
Related workflows
- Prove your meeting-notes pipeline never phones home (and gates on consent)
- Unsloth: write parametric memory in with a fine-tune config
- Validate an Apple Core AI export entry and skill plugin before you touch a Mac
- Serve NVIDIA Nemotron 3 Ultra yourself for high-throughput agents (vLLM)
- Serve GLM-5.1 yourself for long-horizon agentic coding (vLLM)
- Serve MiniMax M3 yourself for agentic coding (vLLM)
Liked this workflow?
Get new verified workflows in WebAfterAI, three issues a week (Tue, Thu, Sat).