Anonymous - 2026-08-04

Originally posted by: AbhishekBarali

Yes, you can reuse the model you already have, and you won't have to download it again.

For a .gguf assistant model

  1. Put your .gguf in the models folder (paths below), keeping the exact filename it has in the Hugging Face repo. The filename is what gets matched.
  2. Open Settings → Models → Add custom model, search for the same repo, and pick the same file.
  3. It appears as already downloaded. SpeakoFlow checks whether the file is on disk before fetching anything, so the download is skipped entirely.

Order matters: move the file into place before step 2, otherwise the download starts and you'd have to cancel it.

If the model is multimodal, the vision projector (mmproj) is a separate file. Drop that in too, using its repo filename, and enable the vision option when you add the model. Anything missing gets fetched; anything already present is left alone.

For a Whisper .bin speech-to-text model

Simply drop it in the same folder and restart the app. Loose .bin files are auto-discovered as custom models on startup, no dialog needed. This currently applies to .bin only, which is why .gguf needs the step above.

Where the models folder is

OS Path
macOS ~/Library/Application Support/com.abhishekbarali.speakoflow/models
Windows %APPDATA%\com.abhishekbarali.speakoflow\models
Linux ~/.local/share/com.abhishekbarali.speakoflow/models (or $XDG_DATA_HOME/...)
Portable install Data/models next to the executable

Your guess was close. It's the bundle identifier rather than the app name, and the folder is models rather than LlamaRuntime. The easiest way to get there on any platform: Settings → About → App Data Directory shows the exact path and has a button to open it in your file manager.

On a custom model path

There's no configurable model directory yet, so today the file does need to live in that folder. If you'd rather not move a 5 GB file at all, run it in Ollama or LM Studio and point SpeakoFlow at that local server under Settings → Assistant. The model stays exactly where it is and the app just talks to it over HTTP.

What's coming

You're right that this should be easier. Plenty of people already have a local model collection and shouldn't have to re-download or hand-copy anything. I'm planning to make this a proper feature: drag and drop a local .gguf or .bin straight into the Models tab to register it, and a configurable models directory so you can point SpeakoFlow at a folder you already use. Thanks for raising it, this is exactly the friction worth removing.