Skip to main content
You can pull any GGUF model from Hugging Face and run it as your local assistant model. Go to Settings → Assistant → Browse and download models, then choose Browse Hugging Face.
This is for assistant models only. Speech-to-text uses the curated catalog in Transcription models, and there is no equivalent search for it.
1

Find a repository

The dialog opens on the most-downloaded GGUF repositories. Type to search by model or creator. Results are ordered by downloads and capped at 25.Each result shows download and like counts, plus a Vision badge when the repository’s tags mark it as multimodal.
2

Choose a quantization

Open a repository and SpeakoFlow lists its downloadable .gguf files, smallest first, with the quantization label pulled out of each filename.Q4_K_M is flagged as recommended. It is usually the best balance of quality, speed, and memory.
3

Optionally include screen vision

If the repository ships a multimodal projector (mmproj-*.gguf), an Include screen vision toggle appears, on by default. It downloads that extra file alongside the weights so the model can read images, which is what Screen vision needs.The toggle does not appear at all when the repository has no projector.
4

Download

The model is added to your catalog immediately and the download starts in the background, so you can close the dialog and watch progress on the model card.
Downloaded custom models appear under Your models in the assistant’s model list, and are deletable like any other.
Custom models are not officially supported. Hardware needs and compatibility vary from model to model, and a model that downloads fine can still fail to load or answer badly.
Only files at the top level of the repository, since those are the ones that can be downloaded directly. Importance-matrix files are filtered out because they are not loadable models.When a repository has several projectors, the higher-precision one is preferred automatically.
SpeakoFlow records where each one came from (repository, download URL, and projector) in a custom_models.json file next to the models. It can re-download one later instead of leaving you with an anonymous .gguf on disk.Downloads use the same resumable, retrying path as the built-in models.
See Models and providers for how a local model fits into the assistant.
Last modified on August 7, 2026