Google · First MLX build 4 Aug 2025
siglip2-base-patch16-224
MLX
apache-2.0
A 375M parameter model from Google, with one MLX build at 8-bit.
- Parameters
- 375M From Hugging Face
- Quantisation
- 8-bit siglip2-base-patch16-224-8bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 399 MB Weights, estimated
- Downloads
- 105 This build, last 30 days
- Task
- —
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/siglip2-base-patch16-224-8bitMLX builds
1 on mlx-community| siglip2-base-patch16-224-8bit | 8-bit | 399 MB | 3 GB | 105 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.