Release notes

What's New

Release notes for LM Mini, LM Mini Home, and Connect. Connect for Mac is deprecated through the end of 2026.

v1.10.7 Oct 26, 2026

Home share: direct Wi-Fi, choose your Mac's model, smoother sync

  • Added a direct Wi-Fi connection between your phone and Mac on the same network: faster, encrypted, and works without internet, with the relay as a fallback
  • Added: pick any model downloaded on your Mac from your phone, and your Mac switches to it
  • Added Keep Mac awake while sharing and Open LM Mini at login on the Mac
  • Added a Get a model button on the Mac sharing screen when no model is downloaded
  • Improved chat sync between your phone and Mac: only changes are sent, pictures and memories come along, edits and deletions sync, and deleted personas and memories stay deleted
  • Improved big models on your Mac get time to load, and your phone shows when your Mac is still loading
  • Improved shared Mac models use a 16K context (8K on 8 GB Macs)
  • Improved your phone suggests updating LM Mini on your Mac when it's out of date
  • Improved Remote Access now says how your connection is protected
  • Improved messages when your Mac's pairing changed and you need to scan the new QR code
  • Changed glass effects are off by default on new installs; turn them on in Appearance
  • Fixes chats with your Mac's models failing when Tool Use is off, in group chats and in Arena
  • Fixes your phone showing no model right after pairing with your Mac
  • Fixes your Mac showing Ready with no model to share
  • Fixes long replies through the relay being cut off as if they were finished
  • Fixes the Mac stopping another app that used the same port

v1.10.5 Oct 24, 2026

Reliability: chats, sync and on-device thinking

  • Improved on-device thinking models like Qwen 3.5: their thinking now goes in the collapsed thoughts section, and you can turn Think off
  • Improved iCloud sync: only chats that changed are uploaded, so it's much lighter on your phone
  • Fixes the chat list and the open chat getting stuck loading until you restart the app
  • Fixes deleted chats and empty New Chats coming back with iCloud sync
  • Fixes the chat still moving while a reply is written when "Follow new replies" is off
  • Fixes large models failing to load over Remote Access with server error 524
  • Fixes the Persona Generator and the News widget using LM Studio instead of Ollama, cloud providers or Apple Intelligence
  • Fixes image generation failing on Automatic1111 after loading a ComfyUI workflow
  • Fixes Ollama replies that stall mid-way being lost; the text already written is kept, with the reason
  • Fixes Pro Search showing "temporarily unavailable" when LM Studio blocks per-request MCPs; you now see which setting to turn on
  • Fixes servers that aren't LM Studio showing "Endpoint not found"; you now see how to add them instead

v1.10.4 Oct 20, 2026

Apple Intelligence & the 2026 models

  • Added Apple Intelligence: chat with the model built into your iPhone, iPad or Mac, with no download (iOS 26 / macOS 26 on supported devices)
  • Added the 2026 on-device models: Qwen 3.5, Gemma 4, Bonsai (1-bit), LFM 2.5, MiniCPM 5, Ministral 3, SmolLM 3 and Granite 4, grouped by family with one "Best quality" pick for your device
  • Improved setup: use Apple Intelligence, download a model, or connect your computer. Servers found on your Wi-Fi now show right on the card
  • Added a chat style choice during setup: full width or bubbles
  • Added LM Mini now asks your name in your first chat and remembers it
  • Added Arena is now free: race models on your own prompts, compare answers side by side, and keep a history of your races
  • Added group chats in folders
  • Added Apple Intelligence as a group chat participant
  • Improved Apple Intelligence replies start faster in longer chats
  • Improved voice chat: tap the mic button to stop recording
  • Improved the home screen with a clearer Chat button and a New Persona tile
  • Improved models you downloaded before stay available under Older models
  • Fixes PDF export failing on Cyrillic, Greek and emoji, and long messages overlapping across pages
  • Fixes Export All Chats garbling non-English text and overwriting chats with the same title
  • Fixes Obsidian exports with invalid frontmatter, and hidden reasoning tags showing in exports
  • Fixes LM Studio failing with "failed to parse grammar" when structured output and web search are both on
  • Fixes long tool and MCP replies from LM Studio ending early
  • Fixes group chats answering with only your main model when it runs on this device
  • Fixes LM Mini Home participants being rejected in group chat setup
  • Fixes No folder not taking a chat out of its folder
  • Fixes Google sign-in on Android

v1.10.3 Oct 14, 2026

Shortcuts MCP tools, Keychain & connection fixes

  • Added your LM Studio MCP tools, like web search, to Siri and Shortcuts
  • Added Turn off Remote Access to the "Can't reach your Mac" message
  • Improved API keys, tokens and server headers are now kept in the Keychain / Keystore instead of plain settings
  • Improved German and Russian voices are now labelled as Piper voices
  • Fixes servers on your local network being blocked on mobile data even when a VPN could reach them; the Wi-Fi notice now only appears when the server really can't be reached, and can be closed for the session
  • Fixes OpenAI-compatible providers like Groq failing with "property 'chat_template_kwargs' is unsupported"
  • Fixes Stop not stopping the reply on your computer over Remote Access and USB, which made your next message wait behind it
  • Fixes USB replies arriving all at once instead of streaming
  • Fixes emoji and non-English text showing broken characters over Remote Access, and LM Mini Home
  • Fixes Remote Access no longer checking your computer after a failed reconnect; models now reload when it's back
  • Fixes Ollama, oMLX, Jan or Unsloth pointing at a dead relay after you turn Remote Access off or unpair
  • Fixes a cleared API key still being sent
  • Fixes Add Server ignoring the headers you entered, so servers behind Cloudflare Access couldn't be added
  • Fixes server addresses ending in /v1 failing, and public addresses without http:// or https:// defaulting to unencrypted http
  • Fixes the model you pick not being the one sent to Ollama, oMLX, Jan, Unsloth and cloud providers
  • Fixes switching servers carrying over the wrong model, such as a GPT model being sent to Mistral
  • Fixes a locked Pro server showing as active while chat used a different server
  • Fixes Siri and Shortcuts using an old server or model after you change settings
  • Fixes group chat sending LM Studio participants to your cloud provider
  • Fixes Ollama group chat participants failing over Remote Access
  • Fixes your LM Studio custom headers and Cloudflare Access secret reaching Unsloth servers and cloud chats
  • Fixes LM Mini Home retrying the relay every second when its session was refused

v1.10.2 Oct 11, 2026

Remote Access switch & clearer connection errors

  • Added a Remote Access on/off switch
  • Added Tap to retry on messages that didn't send
  • Added a mobile data notice when your server only works on Wi-Fi
  • Improved connection errors
  • Improved memories
  • Fixes Pro Search answering without searching when image generation is on
  • Fixes on-device models crashing when the app goes to the background
  • Fixes Kokoro voice crashes, and blocks a voice pack that keeps failing to load
  • Fixes on-device models and voice crashing on older Android phones
  • Fixes Switch provider opening the model list instead of your providers
  • Fixes a failed send leaving the chat stuck on sending
  • Fixes your LM Studio custom headers and Cloudflare Access secret being sent to cloud providers and image servers

v1.9.13 Oct 1, 2026

Apple Watch & Shortcuts

  • Introducing the Apple Watch app for LM Mini
  • Fixes Unsloth showing all models as loaded
  • Fixes being unable to scroll the Unsloth model list
  • Fixes Shortcuts failing over http, so Ask can speak the answer without opening the app
  • Fixes Gemma 3 on-device models failing to load
  • Fixes Feature Requests failing to load before sign-in finished

v1.9.12 Sep 28, 2026

Unsloth context, ComfyUI workflows & clearer limits

  • Added Context Length for Unsloth — the Model Parameters slider loads the model at that size, and asks before reloading if it is already loaded at another size
  • Added Load settings from a ComfyUI workflow, and a name so the next image is saved into that list
  • Added Resize images for physical batch — shrinks a photo when it would be too big for a local model and crash the server
  • Fixes the context bar sitting far below LM Studio — a finished reply uses LM Studio’s own token count, including thinking
  • Fixes high thinking using up the whole reply — Mini tries again with low thinking, and tells you that you can raise max tokens to keep high thinking
  • Fixes an unknown MCP looking like an app bug — Mini says the server rejected that tool, and does not offer Send to support unless it is Pro Search or Code Sandbox
  • Fixes a camera photo disappearing when you come back to the chat
  • Fixes “Loading model” showing again after the reply has already moved on
  • Fixes ComfyUI graphs, including Z-Image, losing the prompt or ignoring the graph’s own sampler
  • Fixes Connect / Share with phone sending image generation to the chat server instead of AUTOMATIC1111 or ComfyUI
  • Fixes the app closing on the splash screen on older iPhones, such as the iPhone 8

v1.9.10 Sep 21, 2026

Full-width chat, gallery & crash fixes

  • Added Unsloth Desktop as a free local OpenAI-compatible provider
  • Added Generated images gallery in the chat ⋯ menu
  • Added website-icon pile for web search sources (tap to expand, tap again for results)
  • Added support tickets can attach the error log
  • Full-width replies is now the default — your messages stay in a bubble, assistant text uses the whole row
  • Improved the chat ⋯ menu (glass) and the streaming status shimmer
  • Hides embedding models from Model Section
  • Fixes attaching a file from Drive / Recents failing with an unknown path
  • Fixes image generation crashing when the server isn't AUTOMATIC1111 (Null is not a List)
  • Fixes two New Chat taps creating the same conversation id
  • Fixes memory extraction still running after you stop a reply
  • Fixes the Voice API-key sheet fighting the keyboard

v1.9.8 Sep 17, 2026

Siri answers, Home personas & clearer host errors

  • Added Siri Ask / Summarize / Translate / Search / News that speak Mini’s reply (iOS 16.4+; stays in Siri on newer iOS)
  • Added Sync personas when Home chat sync is on — pick which personas copy between phone and Mac, including photos and memories
  • Added Full-width replies in Appearance — your messages stay in a bubble, assistant text uses the whole row
  • Added Compress image and resend when LM Studio stops because an attached photo is huge
  • Fixes Face ID / Touch ID unlocking then bouncing straight back to the lock screen
  • Fixes Share with phone on Home dropping after you close the laptop lid and not reconnecting until you refresh
  • Fixes Home sync replacing an existing chat title, and leftover image-prompt text showing in titles
  • Fixes LM Studio / llama.cpp stopping mid-reply looking like a Mini crash — now says the model server stopped, and points at context / max tokens
  • Fixes a sent chat that never reached LM Studio (proxy or tunnel) looking like a Mini bug
  • Fixes Kokoro English voice generating silence

v1.9.5 Sep 15, 2026

Face ID lock, image gen setup & clearer errors

  • Added Face ID, Touch ID, and fingerprint unlock for App Lock
  • Added PIN recovery — sign in and we can email a verification link if you forget the PIN
  • Added Cancel on Hugging Face / LM Studio model downloads
  • Added a prompt to reload the model when you change context length
  • Added a prompt to update image generation when you change the chat server address (and the other way around)
  • Fixes chat stalling or coming back empty while a model is downloading
  • Fixes Live Activities not coming back after you open the app
  • Fixes the chat ⋮ menu crashing
  • Fixes a missing LM Studio MCP (like Playwright) showing up as a Pro Search outage
  • Fixes image generation when ComfyUI or AUTOMATIC1111 isn't running — Mini now says it can't reach them
  • Fixes ComfyUI when there's no checkpoint, or the graph needs your exported workflow
  • Fixes Share with phone / Can't reach your Mac looking like a crash instead of setup help
  • Fixes tools finishing with no reply when max tokens is too low — now says to increase it

v1.9.1 Sep 11, 2026

Low battery, voice playback & Android scroll

  • Added Low battery mode in Appearance — no glass, plain text while the reply streams, Home/iCloud sync after the message finishes
  • Fixes Android chat not following streaming replies (stayed on the start of the bubble until the model finished)
  • Fixes voice mode leaving the mic open after send so Kokoro could not play (iOS CannotInterruptOthers)
  • If the selected model is missing (HTTP 404), shows a banner to pick another model
  • Fixes iOS showing a Local Network permission warning when LM Studio just wasn't serving
  • Fixes app crashing when the PC drops off the network while loading models
  • Fixes chat fonts failing to download — they now come with the app

v1.9.0 Sep 8, 2026

App Lock, JAN AI & Persona Voices

  • Added App Lock (Pro) — set a 4 or 6 digit PIN and choose how long the app can stay closed before asking again
  • Added JAN AI as a local provider
  • Added Ability to assign Kokoro, ElevenLabs or Grok voices to Personas from one dropdown
  • Improved composer tools bar — icons when collapsed, chips when expanded
  • Improved Persona setup — tap Preferred Model to change it, edit avatar from the pencil
  • Fixes tools being sent to models that don't support them
  • Fixes Ollama regenerate going to the wrong backend
  • Fixes App Lock toggle not updating after setting a PIN
  • Fixes Pro tags showing for users who already have Pro
  • Fixes mixed icon styles in Settings

v1.8.22 Sep 2, 2026

ElevenLabs, Grok voices & more languages

  • Fixes Model not found in Group chat
  • Fixes Global Reasoning toggle missing for llama-servers
  • Added French, German, Chinese, Spanish, Russian and more languages to Kokoro
  • Added Forgot Password for Email logins
  • Added ElevenLabs integration for Voices
  • Added Grok AI integration for Voices

v1.8.20 Aug 20, 2026

  • Added Ability to connect with LM Mini Home
  • Added Real-time sync to LM Mini iOS and macOS
  • Added background model downloads and progress notification
  • Added Rolling Conversation in Model Params
  • Added Compact Conversation when Context is 90%
  • Added toggle to disable Glass Effect
  • Added Model Specific Parameters
  • Added ability to save Models Parameters to Personas
  • Fixes Apple Pencil Support
  • Fixes Reasoning Tokens generation even when reasoning is off
  • Fixes videos generation using ComfyUI
  • Fixes long conversation keeps resending whole history
  • Fixes Reasoning not appearing for Llama-server
  • Fixes Title failing to generate for a chat
  • Fixes llama-server reasoning model detection
  • Fixes UI Bugs

v1.8.12 Aug 9, 2026

  • Fixes MCP tools appearing on wrong bubble
  • Fixes SearXNG silently failing
  • Added Loras Support for ComfyUI
  • Fixes Group chat scenario not being registered
  • Fixes Regeneration Icon not appearing

v1.8.10 Aug 1, 2026

  • Fixes Keyboard not closing after sending a message
  • Fixes Reasoning toggle not appearing for some models
  • Fixes scroll getting stuck when reopening old chats
  • Fixes Group chat not able to find certain models
  • Added Scroll to bottom on chats
  • Added ability to work with Gemma thought process
  • Fixes model loading progress bar
  • Fixes chat history not being sent in full for context
  • Fixes invalid calculation of context tokens

v1.8.8 Jul 29, 2026

  • Fixes context window conflicts with LM Studio
  • Fixes Reasoning mode not appearing for some models
  • Fixes Voice chat Reloading model

v1.8.6 Jul 27, 2026

  • Fixes new Persona Screen loading loop
  • Added Chinese app language
  • Fixes Long errors blocking the screen

v1.8.5 Jul 27, 2026

Settings Refresh & Beginner Mode

  • Improved Settings interface — clearer desktop-class layout on Mac and iPad
  • Improved Providers management — easier server and model setup
  • Easy mode for beginners — simpler defaults when Advanced Mode is off
  • Fixed missing quantization labels in Model Management

v1.8.4 Jul 26, 2026

  • Fixes ComfyUI Workflows not displaying on Personas
  • Fixes onDevice models not working with Files
  • Fixes Transcriptions not working for some users
  • Fixes attachments disappearing from chat
  • Fixes chat title generation
  • Added Audio Player for Transcriptions
  • Added support for XLSX and MD files
  • Fixes Pro Search not working at times
  • Fixes on Device model running out of context early
  • Fixes long Prompts in Profile Screen overlapping other elements
  • Fixes MLX no output from model issue

v1.10.7 Oct 26, 2026

Home share: direct Wi-Fi, choose your Mac's model, smoother sync

  • Added a direct Wi-Fi connection between your phone and Mac on the same network: faster, encrypted, and works without internet, with the relay as a fallback
  • Added: pick any model downloaded on your Mac from your phone, and your Mac switches to it
  • Added Keep Mac awake while sharing and Open LM Mini at login on the Mac
  • Added a Get a model button on the Mac sharing screen when no model is downloaded
  • Improved chat sync between your phone and Mac: only changes are sent, pictures and memories come along, edits and deletions sync, and deleted personas and memories stay deleted
  • Improved big models on your Mac get time to load, and your phone shows when your Mac is still loading
  • Improved shared Mac models use a 16K context (8K on 8 GB Macs)
  • Improved your phone suggests updating LM Mini on your Mac when it's out of date
  • Improved Remote Access now says how your connection is protected
  • Improved messages when your Mac's pairing changed and you need to scan the new QR code
  • Changed glass effects are off by default on new installs; turn them on in Appearance
  • Fixes chats with your Mac's models failing when Tool Use is off, in group chats and in Arena
  • Fixes your phone showing no model right after pairing with your Mac
  • Fixes your Mac showing Ready with no model to share
  • Fixes long replies through the relay being cut off as if they were finished
  • Fixes the Mac stopping another app that used the same port

Download LM Mini Home 1.10.7

v1.10.5 Oct 24, 2026

Reliability: chats, sync and on-device thinking

  • Improved on-device thinking models like Qwen 3.5: their thinking now goes in the collapsed thoughts section, and you can turn Think off
  • Fixes the chat list and the open chat getting stuck loading until you restart the app
  • Fixes the chat still moving while a reply is written when "Follow new replies" is off
  • Fixes large models failing to load over Remote Access with server error 524
  • Fixes image generation failing on Automatic1111 after loading a ComfyUI workflow
  • Fixes Ollama replies that stall mid-way being lost; the text already written is kept, with the reason
  • Fixes Pro Search showing "temporarily unavailable" when LM Studio blocks per-request MCPs; you now see which setting to turn on
  • Fixes servers that aren't LM Studio showing "Endpoint not found"; you now see how to add them instead

v1.10.4 Oct 20, 2026

Apple Intelligence & the 2026 models

  • Added Apple Intelligence: chat with the model built into your iPhone, iPad or Mac, with no download (iOS 26 / macOS 26 on supported devices)
  • Added the 2026 on-device models: Qwen 3.5, Gemma 4, Bonsai (1-bit), LFM 2.5, MiniCPM 5, Ministral 3, SmolLM 3 and Granite 4, grouped by family with one "Best quality" pick for your device
  • Improved setup: use Apple Intelligence, download a model, or connect your computer. Servers found on your Wi-Fi now show right on the card
  • Added a chat style choice during setup: full width or bubbles
  • Added LM Mini now asks your name in your first chat and remembers it
  • Added Arena is now free: race models on your own prompts, compare answers side by side, and keep a history of your races
  • Added group chats in folders
  • Added Apple Intelligence as a group chat participant
  • Improved Apple Intelligence replies start faster in longer chats
  • Improved voice chat: tap the mic button to stop recording
  • Improved the home screen with a clearer Chat button and a New Persona tile
  • Improved models you downloaded before stay available under Older models
  • Fixes PDF export failing on Cyrillic, Greek and emoji, and long messages overlapping across pages
  • Fixes Export All Chats garbling non-English text and overwriting chats with the same title
  • Fixes Obsidian exports with invalid frontmatter, and hidden reasoning tags showing in exports
  • Fixes LM Studio failing with "failed to parse grammar" when structured output and web search are both on
  • Fixes long tool and MCP replies from LM Studio ending early
  • Fixes group chats answering with only your main model when it runs on this device
  • Fixes LM Mini Home participants being rejected in group chat setup
  • Fixes No folder not taking a chat out of its folder

v1.10.3 Oct 14, 2026

Shortcuts MCP tools, Keychain & connection fixes

  • Added Turn off Remote Access to the "Can't reach your Mac" message
  • Improved API keys, tokens and server headers are now kept in the Keychain / Keystore instead of plain settings
  • Improved German and Russian voices are now labelled as Piper voices
  • Fixes servers on your local network being blocked on mobile data even when a VPN could reach them; the Wi-Fi notice now only appears when the server really can't be reached, and can be closed for the session
  • Fixes OpenAI-compatible providers like Groq failing with "property 'chat_template_kwargs' is unsupported"
  • Fixes Stop not stopping the reply on your computer over Remote Access and USB, which made your next message wait behind it
  • Fixes USB replies arriving all at once instead of streaming
  • Fixes emoji and non-English text showing broken characters over Remote Access, and LM Mini Home
  • Fixes Remote Access no longer checking your computer after a failed reconnect; models now reload when it's back
  • Fixes Ollama, oMLX, Jan or Unsloth pointing at a dead relay after you turn Remote Access off or unpair
  • Fixes a cleared API key still being sent
  • Fixes Add Server ignoring the headers you entered, so servers behind Cloudflare Access couldn't be added
  • Fixes server addresses ending in /v1 failing, and public addresses without http:// or https:// defaulting to unencrypted http
  • Fixes the model you pick not being the one sent to Ollama, oMLX, Jan, Unsloth and cloud providers
  • Fixes switching servers carrying over the wrong model, such as a GPT model being sent to Mistral
  • Fixes a locked Pro server showing as active while chat used a different server
  • Fixes group chat sending LM Studio participants to your cloud provider
  • Fixes Ollama group chat participants failing over Remote Access
  • Fixes your LM Studio custom headers and Cloudflare Access secret reaching Unsloth servers and cloud chats
  • Fixes LM Mini Home retrying the relay every second when its session was refused

v1.10.2 Oct 11, 2026

Remote Access switch & clearer connection errors

  • Added a Remote Access on/off switch
  • Added Tap to retry on messages that didn't send
  • Added a mobile data notice when your server only works on Wi-Fi
  • Improved connection errors
  • Improved memories
  • Fixes Pro Search answering without searching when image generation is on
  • Fixes on-device models crashing when the app goes to the background
  • Fixes Kokoro voice crashes, and blocks a voice pack that keeps failing to load
  • Fixes Switch provider opening the model list instead of your providers
  • Fixes a failed send leaving the chat stuck on sending
  • Fixes your LM Studio custom headers and Cloudflare Access secret being sent to cloud providers and image servers

v1.9.13 Oct 1, 2026

Apple Watch & Shortcuts

  • Fixes Unsloth showing all models as loaded
  • Fixes being unable to scroll the Unsloth model list
  • Fixes Shortcuts failing over http, so Ask can speak the answer without opening the app
  • Fixes Gemma 3 on-device models failing to load
  • Fixes Feature Requests failing to load before sign-in finished

v1.9.12 Sep 28, 2026

Unsloth context, ComfyUI workflows & clearer limits

  • Added Context Length for Unsloth — the Model Parameters slider loads the model at that size, and asks before reloading if it is already loaded at another size
  • Added Load settings from a ComfyUI workflow, and a name so the next image is saved into that list
  • Added Resize images for physical batch — shrinks a photo when it would be too big for a local model and crash the server
  • Fixes the context bar sitting far below LM Studio — a finished reply uses LM Studio’s own token count, including thinking
  • Fixes high thinking using up the whole reply — Mini tries again with low thinking, and tells you that you can raise max tokens to keep high thinking
  • Fixes an unknown MCP looking like an app bug — Mini says the server rejected that tool, and does not offer Send to support unless it is Pro Search or Code Sandbox
  • Fixes a camera photo disappearing when you come back to the chat
  • Fixes “Loading model” showing again after the reply has already moved on
  • Fixes ComfyUI graphs, including Z-Image, losing the prompt or ignoring the graph’s own sampler
  • Fixes Connect / Share with phone sending image generation to the chat server instead of AUTOMATIC1111 or ComfyUI

v1.9.10 Sep 21, 2026

Full-width chat, gallery & crash fixes

  • Added Unsloth Desktop as a free local OpenAI-compatible provider
  • Added Generated images gallery in the chat ⋯ menu
  • Added website-icon pile for web search sources (tap to expand, tap again for results)
  • Added support tickets can attach the error log
  • Full-width replies is now the default — your messages stay in a bubble, assistant text uses the whole row
  • Improved the chat ⋯ menu (glass) and the streaming status shimmer
  • Hides embedding models from Model Section
  • Fixes image generation crashing when the server isn't AUTOMATIC1111 (Null is not a List)
  • Fixes two New Chat taps creating the same conversation id
  • Fixes memory extraction still running after you stop a reply

v1.9.8 Sep 17, 2026

Home personas, lid-close reconnect & clearer host errors

  • Added Sync personas when Home chat sync is on — pick which personas copy between phone and Mac, including photos and memories
  • Added Full-width replies in Appearance — your messages stay in a bubble, assistant text uses the whole row
  • Added Compress image and resend when LM Studio stops because an attached photo is huge
  • Fixes Share with phone dropping after you close the laptop lid and not reconnecting until you refresh
  • Fixes Home sync replacing an existing chat title, and leftover image-prompt text showing in titles
  • Fixes LM Studio / llama.cpp stopping mid-reply looking like a Mini crash — now says the model server stopped, and points at context / max tokens
  • Fixes a sent chat that never reached LM Studio (proxy or tunnel) looking like a Mini bug
  • Fixes Kokoro English voice generating silence

v1.9.0 Sep 8, 2026

App Lock, JAN AI & Persona Voices

  • Added App Lock (Pro) — set a 4 or 6 digit PIN and choose how long Home can stay closed before asking again
  • Added JAN AI as a local provider
  • Added Ability to assign Kokoro, ElevenLabs or Grok voices to Personas from one dropdown
  • Improved composer tools bar — icons when collapsed, chips when expanded
  • Improved Persona setup — tap Preferred Model to change it, edit avatar from the pencil
  • Fixes tools being sent to models that don't support them
  • Fixes Ollama regenerate going to the wrong backend
  • Fixes App Lock toggle not updating after setting a PIN
  • Fixes Pro tags showing for users who already have Pro
  • Fixes mixed icon styles in Settings

v1.8.20 Aug 20, 2026

  • Connect from iPhone — pair LM Mini with LM Mini Home over Share with phone.
  • Real-time sync — chats stay in sync between LM Mini on iOS and macOS.

v1.8.16 Aug 12, 2026

  • Share with phone — QR pair once. Encrypted relay to your Mac — no port forwarding or VPN.
  • Run models on this Mac — bundled local inference, no Terminal or Homebrew.
  • Share LM Studio & Ollama — phones can use backends already running on the Mac.
  • Desktop shell — nav rail for Chats, Personas, Arena, and Settings.
  • Menu bar — keep Share with phone available while you work in other apps.

Download LM Mini Home — primary Mac app.

Deprecated Connect for Mac keeps working through the end of 2026. New Mac setups: LM Mini Home. Windows and Linux Connect remain current. Why

v1.5.3 Oct 12, 2026

  • Stop really stops — Tapping Stop in LM Mini now stops the reply on your computer too. Before, LM Studio or Ollama kept generating in the background and your next message waited behind it. Works over Remote Access now, and over USB with the next LM Mini app update.
  • Emoji and other languages — Replies with emoji, Chinese, Russian, and other non-English text no longer show broken characters when they stream through Connect.
  • Steady connection after Refresh token — Refreshing the token (or turning the relay off and on) no longer leaves Connect reconnecting every few seconds and dropping your phone's requests.

v1.5.2 Aug 30, 2026

  • Language packs — Download only the voices you need, matching LM Mini: English, Spanish, German, French, Russian, Chinese.
  • Shared Kokoro pack — English, Spanish, French, and Chinese share one multilingual model (~400 MB). The first of those you download unlocks the rest.
  • German and Russian — Kokoro has no DE/RU model; Connect uses small Piper voices (~34 MB each).
  • Chinese (and other scripts) work — Connect no longer defaulted to the English-only engine or dropped CJK lexicons, so Chinese speech synthesizes correctly.

v1.5.1 Aug 24, 2026

  • Kokoro extract on Windows — Download no longer shells out to system tar (that hung on Windows 10). Archives unpack in-process, with a timed fallback.
  • Use folder / Use file — Point Connect at a Kokoro folder you already extracted (7-Zip is fine), or pick the .tar.bz2 yourself. Unlink leaves your files in place.

v1.5.0 Jul 13, 2026

  • Multi-backend remote — Route LM Studio, Ollama, or oMLX through the relay (QR v5 + X-LM-Mini-Backend).
  • Version prompts — Pairing warns when Connect or the mobile app needs an upgrade for multi-backend remote.
  • Provider-aware help — Connection troubleshooting matches the active desktop backend.

v1.4.1 May 8, 2026

  • ComfyUI Streaming Fixes — Resolved an issue causing failures in image generation over remote connections due to proxy timeouts and binary string corruption.
  • Stable Deployments — Simplified desktop deployment pipeline removing blocking validation verifications for cross-platform builds.

v1.4.0 April 26, 2026

  • USB Mode (beta) — Plug your iPhone into your Mac with a USB cable and run LM Studio without Wi-Fi. Perfect for in-flight use, hotels with locked-down networks, or any time you don't want to share Wi-Fi.
  • Free feature — USB Mode is available to everyone on iOS, no subscription required.
  • Auto-detect — LM Mini Connect listens for your iPhone over USB and proxies LM Studio requests through the cable. No IP setup needed.
  • Tray indicator — Menu bar icon flips to a connected variant and shows “iPhone connected via USB” while a phone is attached.

v1.3.0 April 24, 2026

  • New tunnel relay — Connects to relay.lmmini.com (Cloudflare Tunnel + Mac Mini) for faster, more reliable remote access.
  • Dual-relay during transition — Also stays connected to the legacy Cloud Run relay until May 1, 2026, so phones running older versions of LM Mini still pair successfully.
  • Deprecation banners — Surfaces shutdown warnings from the relay so you know when it's time to update.
  • Tougher version check — Reads connect-version.json and uses semver comparison instead of exact-string match.

v1.2.0 April 12, 2026

  • Desktop Kokoro TTS — LM Mini Connect can now run Kokoro text-to-speech locally on your computer and expose it to LM Mini on your phone.
  • Model Downloads in Connect — Download, cancel, remove, and test Kokoro models directly from the desktop app UI.
  • Relay Audio Support — Binary relay forwarding now handles audio correctly, enabling remote Kokoro playback through the relay.
  • Improved Desktop UI — Larger window, clearer Kokoro service status, and better error reporting for downloads and synthesis.