mudler / audio-classification updated 2 months ago

ced-gguf

GGUF quantizations of the CED family (Consistent Ensemble Distillation, Xiaomi) - SOTA-tier audio-tagging models that classify everyday sounds (baby cry, footsteps, glass breaking, alarms, dog bark, ...) into the 527-class AudioSet ontology.

Params
Context
Downloads 30d
922 K
Likes
3
Commercial use: allowed apache-2.0 Not gated GGUF View on Hugging Face ↗

Download history

daily snapshots · 38 days
▲ 110 K in the last 30 days (13.5%)
1.6 M368 K
Aug 14Aug 26Sep 8Sep 20

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
ced-base-q8_0.gguf Q8_0 0.1 GB 0.6 GB ✅ Runs comfortably
ced-base-f32.gguf GGUF 0.3 GB 0.9 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence
apache-2.0
First seen on the Hub
2026-06-21
Training datasets
undisclosed
Added to our catalog
2026-08-14
Compare with any audio-classification model