The wise cheese

Local ML voice chat using high-end models, aiming for a self contained, user-friendly out-of-the-box experience as much as possible.

This is a work in progress with frequent updates; TestFlight builds are available here.

Selection	Full	Mini

A light helper app which can run on an iPhone or device with not enough processing power, which automatically detects and connects to Emeltal on the network and provides the same voice interface. Testflight link for this app is here

Emeltal offers a hand-picked list of proven open-source high-performance models, aiming to provide the best model for each category/size combination. This list often changes and expands as new models become available, or others are superceeded by much better performing ones. All models run at their maximum context size.

• SauerkrautLM-SOLAR
• FusionNet 13b (Truthful_DPO_TomGrc)
• Nous Hermes 2 on Mixtral
• OpenChat 3.5

• Dolphin 2.7 on Mixtral
• Dolphin 2.8 on TinyLlama
• Dolphin 2.2 70b

• Samantha 7b
• Samantha 70b

• Smaug 34b
• Smaug 72b

• Llama 3 70b
• Llama 3 8b

• Dolphin Coder
• Deepseek Coder 33b
• Deepseek Coder 7b
• Everyone Coder
• CodeLlama 70b

• Senku
• MiniCPM-OpenHermes

• MythoMax 13b
• Neural Story

• Whisper

• Emeltal heavily relies on the llama.cpp for LLM processing, and whisper.cpp for voice recognition.
• Text rendering uses Ink to convert between Markdown and HTML.
• Uses my PopTimer for debouncing things.

Released under the terms of the MIT license, see the LICENSE file for license rights and limitations (MIT).

All model data which is downloaded locally by the app comes from HuggingFace, and use of the models and data is subject to the respective license of each specific model.

Copyright (c) 2023-2024 Paul Tsochantaris