MLX Community · First MLX build 24 Apr 2024
OpenELM-450M-instruct
MLX
apple-sample-code-license
A 457M parameter model, with 2 MLX builds at 8-bit.
- Parameters
- 457M From Hugging Face
- Quantisation
- 8-bit OpenELM-450M-instruct-8bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 486 MB Weights, estimated
- Downloads
- 19 This build, last 30 days
- Task
- —
- MLX builds
- 2 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/OpenELM-450M-instruct-8bitMLX builds
2 on mlx-community| OpenELM-450M-instruct-8bit | 8-bit | 486 MB | 3 GB | 19 |
|---|---|---|---|---|
| OpenELM-450M-Instruct | Unstated | 914 MB | 4 GB | 17 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.