Cursor and Local Qwen Are Not the Same Qwen

Cursor’s chat model, a cloud Qwen you add in Cursor settings, and a Qwen that runs on your Mac are three different meters. You keep talking to Cursor. Cursor stays the conductor. When the work is a GCT screen, a Content Factory first draft, or a weekly MAA, the agent on the Mac should send that slice to local Qwen at 127.0.0.1:8080 so you do not burn Cursor tokens. Cursor Auto does not natively pick a localhost model. The automatic path is standing agent judgment plus a Cursor rule, not a model-picker switch. The living token-and-dollar meter on this page is how we show, in public, how much work actually went to Qwen.

On a phone those three cards stack. The rule does not change: keep talking to lane 1; send first drafts to lane 3; do not paste localhost into lane 2.

What problem does this page solve?

People install a local Qwen, then open Cursor, see a Qwen option (or Override OpenAI Base URL), and assume that is the same server. It is not. I mixed them up on this desk until 25 August 2026, when we stood up official mlx-community/Qwen3.8-27B-4bit on a MacBook Pro with 128 GB of unified memory, bound to http://127.0.0.1:8080/v1, and watched agents treat “Qwen” as one blob.

This page is the routing map. The install recipe lives next door: How to install local Qwen (MLX, no Ollama). Anyone who already installed Qwen on a Mac can use the same Cursor rule and the same Content Factory jobs without inventing a second stack.

This is the same ladder as how we taught Claude to pick its own model: judgment stays on the expensive conductor. Bulk first drafts go to a cheaper worker. Local Qwen is the electricity-only rung under that bulk tier. Hosted Kimi is a different worker on a different meter — see Kimi K3 vs Claude, Content Factory math. The personal playbook — how I actually sit at the desk, next to How I Use Grok Bot and How to Use Claude — lives at How I Use Local Qwen. We publish the worker meter in public because that is the deal in Building in Public: show the work while we do it, including how much load is still on Cursor versus what actually hit the Mac.

What are the three Qwens?

Cursor staff have been explicit about the middle vs right lane. Override OpenAI Base URL and custom models go through Cursor’s servers so they can build prompts. Those servers cannot open http://127.0.0.1:8080 on your laptop. Putting localhost in the model picker fails. Forum receipt: Connecting local AI server to Cursor does not work (staff: localhost is not supported; expose a public HTTPS endpoint if you insist on picker-as-model). A public HTTPS tunnel would make the Mac reachable, and would also replace the conductor with the worker. Do not do that for Content Factory work. Keep Grok or Claude in the chat. Let the agent curl the Mac.

One more trap: Override OpenAI Base URL is global. Turn it on to point at a tunnel and you can capture Cursor’s built-in models too. That is the opposite of “talk to Cursor, draft on the Mac.”

Is the ideal possible — I only talk to Cursor, and Cursor just knows?

Yes, at the agent layer. No, as a Cursor Auto product feature.

Cursor Auto (and the model picker) do not inventory a local MLX server and route “this looks cheap” to it. There is no hidden pool that includes 127.0.0.1.

What works today: you keep one conversation with Cursor. The agent running in that chat has tools on the Mac. A standing always-on rule says: if the task is a GCT screen, a factory first draft, or a weekly MAA, call local Qwen without asking me first. The HTTP request never leaves the laptop. Cursor tokens are spent on the conductor’s thinking and tool use, not on generating the 800-word first draft.

That is the same pattern as model judgment. The conductor is not dumber. It is refusing to spend premium tokens on mechanical work. If local Qwen is down, the agent runs qwen up (first start is slow; weights load into unified memory) and retries. If the machine has no MLX stack, it says so and stays on the Cursor model instead of inventing a fake local call.

You should see the handoff in the chat: a terminal call, a curl to port 8080, or qwen gct / qwen factory / qwen maa. If you never see a local command, you are still burning Cursor tokens for that draft.

When should Cursor send work down, without being asked?

Local Qwen stages. The conductor still owns the gate. That is how a digital marketing agency can give every installer the same win: Cursor remains the operator; the Mac becomes the intern who drafts overnight without a token bill.

The factory line on this page is Produce → Process → Post → Promote. The fuller operating contract on the factory hub also names Plumbing and Perform around that line. Local Qwen drafts the line. It does not run plumbing, and it does not perform the publish.

How does a Content Factory / Local Service Spotlight agent actually call it?

On a machine that followed the install page:

qwen status
qwen up          # if 8080 is down
qwen ping        # expect PONG
qwen gct
qwen factory
qwen maa

OpenAI-compatible shape, so Claude Code, Codex, a Python script, or LangGraph can use the same worker:

POST http://127.0.0.1:8080/v1/chat/completions
Authorization: Bearer local
model: mlx-community/Qwen3.8-27B-4bit

Team checkout: ~/Projects/agent-runtime/local-qwen-agents/. Command on PATH: qwen. This is not Kimi Code. kimi is Moonshot’s hosted CLI. Do not point Kimi at port 8080 unless you mean to.

Factory canon stays at Content Factory. GCT canon stays at GCT (the qualification screen lives with Social Amplification). Weekly MAA stays at MAA. This page does not fork those. It says which engine drafts them.

25 August 2026 receipts on this Mac: GET /v1/models listed the 4-bit id; qwen ping returned PONG; a sample GCT returned DISCOVERY_REQUIRED in about 63 seconds at roughly 17 tokens per second decode. Treat those as one machine’s numbers, not a promise.

What should other people who installed Qwen do in Cursor?

1. Leave Cursor’s model on your judgment engine (Claude, Grok, GPT). Do not paste http://127.0.0.1:8080 into Override OpenAI Base URL.
2. Drop in an always-on Cursor rule: local Qwen is the worker; delegate GCT / factory / MAA first drafts without being asked; never send, publish, or spend from that worker. Copy the file from the install page, or use local-qwen-agents/cursor-rule.mdc in the team runtime.
3. Point the agent at your install README so the port, model id, and start command are not tribal knowledge.
4. Treat cloud Qwen in Cursor settings as a third vendor. Label the keys. Do not assume it is the Mac.

New agents in our shop still start at New agents start here. Skills vs routines still live at Skills and routines. Where agents talk still lives at Where your agents talk. Application Passwords still live at Application Passwords. Basecamp writes still follow post to Basecamp.

FAQ

Can I set local Qwen as the Cursor model so every keystroke is free?

Not through Cursor’s official custom-model path. Cursor’s servers would have to reach your loopback address. They cannot. Tunneling localhost to a public HTTPS URL is possible and is the wrong architecture for this job: you would demote the conductor, expose an unauthenticated MLX server, and (because the override is global) risk capturing the built-in models you wanted to keep.

Does Cursor Auto already send cheap work to my Mac?

No. Auto picks among Cursor’s cloud models. Local Qwen is reached when the agent runs a local command or HTTP call.

Is the Qwen in Cursor settings my local server?

Only if you deliberately pointed BYOK at a public URL that happens to terminate on your machine. The default Qwen options are cloud vendors. Our recommended local stack never leaves 127.0.0.1.

Is this Kimi?

No. Kimi Code is a hosted coding CLI. Local Qwen on this desk is MLX on Apple Silicon. Workers are auditionable; they are not interchangeable names.

Will local Qwen publish my WordPress or send my email?

No. Stage only. Application Passwords, Gmail drafts, and Basecamp writes stay on the conductor.

Does client copy leave the laptop when the agent uses local Qwen?

The completion request goes to loopback. It does not go to Alibaba, OpenRouter, or Cursor’s model API. The conductor’s own thinking still runs in Cursor cloud, so prompts and tool traces there follow Cursor’s product. That is why we keep secrets out of the local prompt and out of git.

Can Claude Code, Codex, or a Python job use the same Qwen?

Yes. Same OpenAI-compatible /v1. That is the point of staying on port 8080 instead of a Cursor-only plugin.

What if port 8080 is down or this machine has no MLX?

The agent runs qwen up once, waits for qwen ping, then drafts. If ping still fails, it says so and stays on the Cursor model. It does not fake a local call.

What model and port are we running in August 2026?

Official mlx-community/Qwen3.8-27B-4bit (~16 GB) via python -m mlx_vlm.server on port 8080. Qwen3.8 is a vision-language model; mlx-lm cannot load it.

How much money does this save?

Local Qwen’s API line is zero. Cursor still bills the conductor. The meter on this page converts worker tokens to Anthropic list prices so we can see the avoided draft cost. Day one is pennies. That is the honest number. The Claude sibling of this meter is the itemized Claude usage log. Agents refresh the block without waiting to be asked, about once a day when new completions exist.

Install and verify: How to install local Qwen (MLX, no Ollama). Desk playbook: How I Use Local Qwen. Directory of every other canonical URL: blitzmetrics.com/canonical/.