MLX Community · First MLX build 2 Apr 2025
all-MiniLM-L6-v2
MLX
Text apache-2.0
A 23M parameter sentence similarity model, with 4 MLX builds, from 4-bit to bf16.
- Parameters
- 23M From Hugging Face
- Quantisation
- 4-bit all-MiniLM-L6-v2-4bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 13 MB Weights, estimated
- Downloads
- 6.3K This build, last 30 days
- Task
- Sentence similarity Text
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at 4-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/all-MiniLM-L6-v2-4bitMLX builds
4 on mlx-community| all-MiniLM-L6-v2-4bit | 4-bit | 13 MB | 3 GB | 6.3K |
|---|---|---|---|---|
| all-MiniLM-L6-v2-6bit | 6-bit | 18 MB | 3 GB | 48 |
| all-MiniLM-L6-v2-8bit | 8-bit | 24 MB | 3 GB | 74 |
| all-MiniLM-L6-v2-bf16 | bf16 | 45 MB | 3 GB | 184 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.