HF Model & Benchmark Matrix

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

Voxtral-4B-TTS-2603

mistralai/Voxtral-4B-TTS-2603

kind
original
quant
bf16 (16-bit)
family
mistral
modality
text-to-speech
root model
mistralai/Ministral-3-3B-Base-2512
provider
mistralai
license
cc-by-nc-4.0
language
en, fr, es, pt, it, nl, de, ar, hi
context
—
library
vllm
vRAM (GB)
—
size on disk
—
downloads
3,954
likes
889
created
—
last modified
2026-03-31T13:43:59+00:00 (2026)
huggingface
https://huggingface.co/mistralai/Voxtral-4B-TTS-2603
tags
vllmmistral-commontext-to-speechenfresptitnldearhiarxiv:2603.25551base_model:mistralai/Ministral-3-3B-Base-2512base_model:finetune:mistralai/Ministral-3-3B-Base-2512license:cc-by-nc-4.0region:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
RTFspeech-asr10.3low| 1 | 70 ms | 0.103 | 119.14 |

Discussions (0)

none scraped.

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