MLX Community · First MLX build 2 Apr 2025
bge-small-en-v1.5
MLX
Text mit
A 33M parameter embeddings model, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 33M From Hugging Face
- Quantisation
- bf16 bge-small-en-v1.5-bf16
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 67 MB Weights, estimated
- Downloads
- 868 This build, last 30 days
- Task
- Embeddings Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at bf16
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/bge-small-en-v1.5-bf16MLX builds
4 on mlx-community| bge-small-en-v1.5-4bit | 4-bit | 19 MB | 3 GB | 199 |
|---|---|---|---|---|
| bge-small-en-v1.5-6bit | 6-bit | 27 MB | 3 GB | 130 |
| bge-small-en-v1.5-8bit | 8-bit | 36 MB | 3 GB | 500 |
| bge-small-en-v1.5-bf16 | bf16 | 67 MB | 3 GB | 868 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.