MLX Community · First MLX build 11 Jan 2024
multilingual-e5-large
MLX
Text mit
A 560M parameter embeddings model, with 2 MLX builds.
- Parameters
- 560M From Hugging Face
- Quantisation
- Unstated multilingual-e5-large-mlx
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 282 This build, last 30 days
- Task
- Embeddings Text
- MLX builds
- 2 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
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/multilingual-e5-large-mlxMLX builds
2 on mlx-community| multilingual-e5-large | Unstated | 1.1 GB | 4 GB | 136 |
|---|---|---|---|---|
| multilingual-e5-large-mlx | Unstated | — | — | 282 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.