Qwen2.5-Omni-7B-GPTQ-Int4

Home/Models/Qwen/Qwen2.5-Omni-7B-GPTQ-Int4

Qwen/Qwen2.5-Omni-7B-GPTQ-Int4

kind: gptq
quant: gptq
family: qwen
modality: any-to-any
root model: Qwen/Qwen2.5-Omni-7B
provider: Qwen
license: other
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 1,544
likes: 14
created: —
last modified: 2025-05-15T10:09:01+00:00 (2025)
huggingface: https://huggingface.co/Qwen/Qwen2.5-Omni-7B-GPTQ-Int4
tags: transformerssafetensorsqwen2_5_omnitext-to-audiomultimodalany-to-anyenarxiv:2503.20215license:otherendpoints_compatible4-bitgptqregion:us

benchmark	category	score	context	conf	evidence
MMLU-Pro	knowledge	47.0	MMLU-Pro	medium	`\| MMLU-Pro \| Text -> Text \| Accuracy ⬆️ \| 47.0 \| 43.76 \|`
WER LibriSpeech	speech-asr	3.4	LibriSpeech test-other	medium	`\| LibriSpeech test-other \| ASR \| WER ⬇️ \| 3.4 \| 3.71 \|`

none scraped.