HF Model & Benchmark Matrix

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

Voxtral-Mini-4B-Realtime-2602-GGUF

Bercraft/Voxtral-Mini-4B-Realtime-2602-GGUF

kind
gguf
quant
gguf (16-bit)
family
misc
modality
automatic-speech-recognition
root model
mistralai/Ministral-3-3B-Base-2512
provider
Bercraft
license
apache-2.0
language
en, fr, es, de, ru, zh, ja, it, pt, nl, ar, hi
context
—
library
vllm
vRAM (GB)
—
size on disk
—
downloads
200
likes
0
created
—
last modified
2026-05-18T09:46:07+00:00 (2026)
huggingface
https://huggingface.co/Bercraft/Voxtral-Mini-4B-Realtime-2602-GGUF
tags
vllmggufvoxtral_realtimemistral-commonautomatic-speech-recognitionenfresderuzhjaitptnlarhikoarxiv:2602.11298base_model:mistralai/Ministral-3-3B-Base-2512base_model:quantized:mistralai/Ministral-3-3B-Base-2512license:apache-2.0region:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
WER AMIspeech-asr14.43GigaSpeech 2k Subset | GISpeech 2k Subsetlow| Voxtral Mini Transcribe 2.0 | Offline | 10.39% | 6.81% | 14.43% | 11.54% | 10.42% | 1.74% |
WER Switchboardspeech-asr11.54GigaSpeech 2k Subset | GISpeech 2k Subsetlow| Voxtral Mini Transcribe 2.0 | Offline | 10.39% | 6.81% | 14.43% | 11.54% | 10.42% | 1.74% |
WER GigaSpeechspeech-asr6.81GigaSpeech 2k Subset | GISpeech 2k Subsetlow| Voxtral Mini Transcribe 2.0 | Offline | 10.39% | 6.81% | 14.43% | 11.54% | 10.42% | 1.74% |
WER TED-LIUMspeech-asr2.86low| Voxtral Mini Transcribe 2.0 | Offline | 4.08% | 9.81% | 11.69% | 2.86% |

Discussions (0)

none scraped.

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