Parameters
—
Weights (est.)
—
Mac memory (est.)
—
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- google/siglip2-so400m-patch16-512 (adapter)
- Vendor
- Google · Gemma
- Task
- Image classification
- Quantisation
- Not stated
- Licence
- apache-2.0
- Downloads
- 21 in the last 30 days · 221 all time · 1 likes
- Published
- 2026-06-06 · updated 2026-06-06 (5mo ago)
- Tags
- image-quality-assessment, nr-iqa, siglip2, lora