vit-age-classifier
r = requests.get('https://github.com/dchen236/FairFace/blob/master/detectedfaces/raceAsianface0.jpg?raw=true') im = Image.open(BytesIO(r.content))
Params
90 M
Context
—
Downloads 30d
248 K
Likes
148
Download history
daily snapshots · 9 days248 K197 K
Sep 12Sep 15Sep 18Sep 20
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | f32 | 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
- Architecture
- ViTForImageClassification
- Parameters
- 90 M
- Tensor type
- F32
- Layers / heads
- 12 / 12
- First seen on the Hub
- 2022-03-02
- Training datasets
- nateraw/fairface
- Added to our catalog
- 2026-09-12
Compare with any image-classification model