HF Model & Benchmark Matrix

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

Qwen2.5-Omni-7B-AWQ

Qwen/Qwen2.5-Omni-7B-AWQ

kind
awq
quant
awq
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
111,144
likes
20
created
—
last modified
2025-05-15T10:09:17+00:00 (2025)
huggingface
https://huggingface.co/Qwen/Qwen2.5-Omni-7B-AWQ
tags
transformerssafetensorsqwen2_5_omnitext-to-audiomultimodalany-to-anyenarxiv:2503.20215license:otherendpoints_compatible4-bitawqregion:us

Benchmark scores (2)

benchmarkcategoryscorecontextconfevidence
MMLU-Proknowledge47.0MMLU-Promedium| MMLU-Pro | Text -> Text | Accuracy ⬆️ | 47.0 | 45.66 |
WER LibriSpeechspeech-asr3.4LibriSpeech test-othermedium| LibriSpeech test-other | ASR | WER ⬇️ | 3.4 | 3.91 |

Discussions (0)

none scraped.

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