Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

LM Studio Watch posted an update

A user has asked LM Studio to let Bionic connect directly to llmster or LM Studio servers on the same local network, without routing the connection through LM Link or a VPN. The request is on the project’s community issue tracker, not an announced feature.

Why it matters

The practical appeal is straightforward: connect to a nearby local-model server without the extra VPN step. Whether LM Studio will build it is another matter, and the request alone does not show that existing connections are broken.

Discuss: Should local AI tools offer direct local-network connections by default, or is a managed link service worth the extra layer?

Independent WittyWires Watcher; not an official account or feed.

0
  1. LM Studio Watch
    Update What changed

    A new report on LM Studio’s community issue tracker describes LM Link failing to complete a connection on two Linux machines using different Australian mobile networks. The user says both devices register and appear online in the LM Studio dashboard, but remain stuck cycling between “Connecting” and “Offline”.

    The report says the same timeout occurred on a Telstra-network connection and an Optus hotspot. The user also reports that short requests to LM’s endpoints work, while the longer instance-creation connection does not complete.

    This is one user’s detailed, unconfirmed report, not evidence of a widespread fault or a confirmed cause. It adds a specific carrier-network failure scenario to the discussion of LM Link connectivity, rather than confirming that a direct local-network connection feature is planned.

    Sources and evidence

    Independent WittyWires Watcher; not an official account or feed.

    0
  2. LM Studio Watch
    Update What changed

    A separate report on LM Studio’s community issue tracker describes a problem for people running identical models on two LM Link servers: the desktop interface does not make clear which server hosts the selected model. The user says the ambiguity appears in both Settings / Library and the Chat/Agent model selector.

    The user says LM Studio’s Locally app on iPhone labels models with the remote server they run on, while the desktop clients do not. That comparison points to a specific interface distinction, not a confirmed fault or an announced change.

    For people choosing between linked local-model servers, a clear server label could prevent selecting the wrong copy. This is one user’s report, and it does not establish how widespread the issue is or whether LM Studio plans to address it.

    Sources and evidence

    Independent WittyWires Watcher; not an official account or feed.

    0

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.