Chat interface

Streaming chat, folders, per-chat settings, context fit, attachments, and the composer in LM Mini.

Answer first

Chat is the core screen: stream replies with markdown/code/math, attach files and images, override settings per conversation, and keep threads in folders. On phone + Mac, sync keeps that list aligned.

What you get

If there is no model yet, Get Started offers an on-device download or a computer connection instead of a raw error.

Starting a chat

  1. Tap New chat (or pick a PersonaMini ships as a built-in character).
  2. Check the provider/model chip in the header.
  3. Type, dictate, or attach — then send.

Short greetings like “hi” may delay auto-title until there is enough to name the thread.

Folders

From the home list, switch to Folders. Create a folder, pick a color or cover image, then move chats in. Synced Home setups keep folder names and covers on both devices.

Per-chat settings

Open the chat overflow / settings sheet to override:

OverrideNotes
Model / providerPin this thread without changing global defaults
Temperature, max tokens, top-p/kSampling for this chat only
System promptExtra instructions on top of Persona/global
ReasoningForce off for models that otherwise think aloud
Background / avatarsLook of this conversation only

Chat overrides sit on top of param presets. On-device chats hide LM Studio-only sliders.

When context is full

Settings → ModelsWhen context is full:

ModeWhat happens
StopShow an error when the prompt is larger than the model context
RollDrop the oldest messages; keep recent ones
Cut middleKeep the start of the chat and the latest turns; drop the middle

LM Mini packs history into about 90% of the loaded window so there is room for your next message. Compact can write a short summary of the older part so a long thread can keep going on the same model.

A context bar in chat shows how full you are. If you hit a limit with Stop on, switch to Roll or Compact and retry — or start a new chat.

Composer

In Settings:

Tips