This Hugging Face repository hosts GGUF quantized files for Voxtral-Small-24B-2507, an open audio LLM capable of automatic speech recognition across 8 languages. It is designed for local inference using tools such as transcribe.cpp and supports multiple quantization levels for different hardware configurations.
In the Speech to text space, Voxtral Small 24B 2507 takes a focused approach. It focuses on running high-quality open-source speech recognition and audio-language models locally with efficient quantized formats. Voxtral Small 24B 2507 is an open-source project aimed at developers. The project is open source (MIT). Voxtral Small 24B 2507 is available on the command line, and it can be self-hosted.
It is developed by handy-computer, and it first shipped in 2026. Development happens publicly on GitHub with 1.4k stars and 419 commits in the last 90 days. Among its 4 catalogued features are speech-to-Text, Multilingual ASR, and GGUF Quantization.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do