HF Model & Benchmark Matrix

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

Kimi-Audio-7B-Instruct

tunglinwood/Kimi-Audio-7B-Instruct

kind
original
quant
bf16 (16-bit)
family
kimi
modality
text-to-speech
root model
moonshotai/Kimi-Audio-7B
provider
tunglinwood
license
—
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
7
likes
0
created
—
last modified
2026-02-12T04:59:27+00:00 (2026)
huggingface
https://huggingface.co/tunglinwood/Kimi-Audio-7B-Instruct
tags
kimi-audiosafetensorsaudioaudio-language-modelspeech-recognitionaudio-understandingtext-to-speechaudio-generationchatcustom_codeenzhlicense:mitregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.

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