HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Voxtral-Small-24B-2507-gguf

handy-computer/Voxtral-Small-24B-2507-gguf

kind
gguf
quant
gguf (16-bit)
family
misc
modality
automatic-speech-recognition
root model
mistralai/Voxtral-Small-24B-2507
provider
handy-computer
license
apache-2.0
language
en, fr, de, es, it, pt, nl, hi
context
,
library
transcribe.cpp
vRAM (GB)
—
size on disk
—
downloads
181,648
likes
0
created
—
last modified
2026-06-28T13:16:39+00:00 (2026)
huggingface
https://huggingface.co/handy-computer/Voxtral-Small-24B-2507-gguf
tags
transcribe.cppggufasrspeech-to-textvoxtralaudio-llmmultilingualautomatic-speech-recognitionenfrdeesitptnlhiarxiv:2507.13264base_model:mistralai/Voxtral-Small-24B-2507base_model:quantized:mistralai/Voxtral-Small-24B-2507license:apache-2.0region:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WERspeech-asr1.56low| BF16 | [Voxtral-Small-24B-2507-BF16.gguf](https://huggingface.co/handy-computer/Voxtral-Small-24B-2507-gguf/resolve/main/Voxtral-Small-24B-2507-BF16.gguf) | 48.54 GB | 1.56% |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.