MERT-v1-330M vs audiobox-aesthetics
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | MERT-v1-330M | audiobox-aesthetics |
|---|---|---|
| Parameters | — | 100 M |
| Architecture | MERTModel | — |
| Context length | — | — |
| Licence | cc-by-nc-4.0 | cc-by-4.0 |
| Commercial use | Not allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 559,539 | 400,930 |
| Downloads all time | 2.4 M | 2.3 M |
| Quantizations on the Hub | — | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-03-17 | 2025-02-13 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
581 K321 K
MERT-v1-330M
audiobox-aesthetics
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
audiobox-aesthetics · fp16
1.0 GB / 24 GB
Adjacent comparisons
clap-htsat-fused vs MERT-v1-330M
clap-htsat-fused vs audiobox-aesthetics
ast-finetuned-audioset-10-10-0.4593 vs MERT-v1-330M
ast-finetuned-audioset-10-10-0.4593 vs audiobox-aesthetics
wav2vec2-large-robust-12-ft-emotion-msp-dim vs MERT-v1-330M
wav2vec2-large-xlsr-53-gender-recognition-librispeech vs MERT-v1-330M