VibeVoice-Large-AWQ

Home/Models/ncoder-ai/VibeVoice-Large-AWQ

ncoder-ai/VibeVoice-Large-AWQ

kind: awq
quant: awq
family: misc
modality: text-to-speech
root model: rsxdalv/VibeVoice-Large
provider: ncoder-ai
license: mit
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 406
likes: 1
created: —
last modified: 2026-05-07T16:39:50+00:00 (2026)
huggingface: https://huggingface.co/ncoder-ai/VibeVoice-Large-AWQ
tags: transformerssafetensorsvibevoicetext-to-speechttsawqint4quantizedenbase_model:rsxdalv/VibeVoice-Largebase_model:quantized:rsxdalv/VibeVoice-Largelicense:mitendpoints_compatible4-bitregion:us

benchmark	category	score	context	conf	evidence
RTF	speech-asr	54.0	RTF (i5-12600K, 7 steps)	medium	`\| RTF (i5-12600K, 7 steps) \| 0.54 \| 1.220 \| 0.699 \|`
RTF	speech-asr	50.9	RTF (i7-14700KF, 5 steps)	medium	`\| RTF (i7-14700KF, 5 steps) \| 0.509 \| 0.860 \| 0.457 \|`

none scraped.