Compute / Providers

Troubleshoot the MLX compute agent on your Mac

A loaded background service can still have no model ready to serve. Check the agent, Python environment and local model endpoint separately to find where setup stops.

By PROXIES.SX. Sources reviewed .

The decision in detail Reviewed 11 Sep 2026

Find the first failed stage before reinstalling.

An online agent, a serving model, a passed benchmark and an approved listing are separate states. Check runtime logs and the farmer dashboard together before changing a working installation.

Documented heartbeat interval
60 seconds
Missing-heartbeat offline threshold
3 minutes
Reviewed agent release
0.3.1
  1. Agent cannot start

    Check native arm64 Node 18+, Python 3.10+, macOS 14+ and runtime logs.

  2. Model cannot become ready

    Check disk space, download progress, the pinned revision and startup generation errors.

  3. Node is paused or offline

    Check power, thermal state, sleep and heartbeat. launchd does not keep a closed laptop awake.

  4. Ready but not listed

    Review benchmark status, the countersigned agreement and separate admin approval.

A diagnostic path based on the current agent reference, not a report of faults in your node. Redact keys from logs before requesting support.

Check the installed agent version first

Use the installed copy when it exists, so you inspect the version launchd actually starts. The September 11 source review covers agent 0.3.1. Its installer copies the script to ~/.proxies-compute and uses a pinned Python runtime. Compute agent source

node ~/.proxies-compute/compute-agent.js --status

If that file does not exist, inspect the original download and follow the current provider setup. A farmer account, verified email and compute supply key are required. A renter inference key is a different credential.

A status report distinguishes the service from the model endpoint. A loaded launchd service can still be downloading a model or waiting for approval. Read the node's state in the farmer Compute dashboard alongside the local result.

Diagnose architecture and Python runtime errors

The agent checks for native arm64 Node and Python. These read-only commands report the executables you are using:

node -p 'process.arch'
python3 -c 'import platform, sys; print(platform.machine()); print(sys.version)'
sw_vers -productVersion

The documented minimums are macOS 14, Node.js 18, Python 3.10 and 24 GB of memory on Apple Silicon. Use a currently supported Node release that meets those checks. Release schedule

Agent 0.3.1 installs packages under ~/.proxies-compute/runtime-0.31.3. A terminal reporting mlx_lm.server: command not found does not establish that this private runtime is broken. Inspect the installer's Python directly:

~/.proxies-compute/runtime-0.31.3/bin/python3 -m pip show mlx-lm mlx transformers

That path is version-specific. For a later agent, read its runtime path before copying the command. Avoid replacing the pinned packages with a global pip install as a first repair. Python environments have their own packages and executable paths. Python environment behavior

Check free disk and the pinned model download

The smallest installation requires at least 26 GB free. The agent checks the volume that holds the Hugging Face cache, which can differ from your home volume when HF_HOME or HF_HUB_CACHE is configured. Larger models need more headroom. Agent disk checks

A repository directory can exist while its requested revision is incomplete. The source checks the revision snapshot for configuration and weight files before serving it. Hugging Face supports downloads by full commit hash; compare the expected hash with the catalog revision. Hub download documentation

Preserve the first download error and check connectivity to that repository. Do not delete the entire shared cache as a routine fix. Other applications may use its files.

Check the local model endpoint

The default server listens on loopback port 8734. Substitute your configured MLX_PORT if different:

curl --fail --show-error --max-time 5 http://127.0.0.1:8734/v1/models

A successful response means a local server answered. Compare its model with the assigned snapshot; another process on that port does not establish readiness. Connection refusal means nothing accepted that connection at that moment. It does not diagnose an account problem by itself.

Avoid starting a second model server on the agent's port. The agent manages its serving process. If you reinstall to repair the runtime, allow for a restart and coordinate an actively rented node's interruption first.

Match the dashboard state to the next check

ObservationNext check
No registered nodeVerify the farmer account and compute supply key, then read registration errors.
Downloading or loadingCheck the first error, cache volume space, exact model revision and memory.
Ready locally, offline in the portalCheck internet access and heartbeat errors. The documented offline threshold is three minutes without a heartbeat.
Paused for battery or thermal conditionsRestore power or cooling and inspect the reported pause reason.
Verified but cannot listCheck supplier approval and the signed, countersigned Partner Agreement.
Repeated server restartsRecord the initial runtime error before restarting again. The agent limits restart attempts.

These are diagnostic steps derived from the published source and provider admission documentation. They are not results from a completed provider installation.

Collect useful evidence for support

The default log is ~/Library/Logs/proxies-compute.log. Share a short redacted excerpt around the first failure with the time, agent version, macOS version, memory and model ID. Keep the API key, private device identifiers and customer prompts out of public reports.

The current executable constant sets a 175-second generation deadline and a 60-second gap-without-output deadline. An older comment still mentions 300 seconds; the executable constant is the basis for this guide. The customer documentation allows up to three minutes for a non-streaming response. These are recovery limits, not measured latency or capacity. Agent source, customer API documentation

Use the benchmark worksheet to record prompt length, output length and concurrency when a specific workload times out. When the node is ready and approved, list it in the farmer portal and track income through your account's earnings and cost calculation.

Sources and references

Reviewed September 11, 2026. Product statements come from public APIs, provider documentation and published application code. Technical references explain the evaluation methods. Authenticated rental and payout behavior has not been tested.

  1. Compute operation and pricing reference. PROXIES.SX.
  2. Compute provider documentation. PROXIES.SX.
  3. Compute agent source. PROXIES.SX.
  4. Customer documentation in the compute application. PROXIES.SX.
  5. Download files from the Hub. Hugging Face.
  6. Python virtual environments. Python Software Foundation.
  7. Node.js release schedule. Node.js project.

Saved product API responses

Your farmer account is required to provide compute

Create an account at farmer.proxies.sx, verify your email, sign the Partner Agreement and create a compute supply key on the Compute page. Install the agent, complete its benchmark and supplier approval, review the approved price and share, then list the node. Manage compute nodes, listings, earnings and payout requests in that account.

Create provider account

Dated research and worked examples. No paid rental, provider payout or hardware benchmark was performed for this guide. Sources appear alongside the claims they support. Back to the compute overview.