zed-industries · First MLX build 16 Feb 2025
zeta
MLX
apache-2.0
A 7.6B parameter model from zed-industries, with 4 MLX builds, from 4-bit to fp16.
- Parameters
- 7.6B From Hugging Face
- Quantisation
- 8-bit zed-industries-zeta-8bit
- Memory needed
- 12 GB Estimate, unified memory
- Download
- 8.1 GB Weights, estimated
- Downloads
- 102 This build, last 30 days
- Task
- —
- MLX builds
- 4 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 12 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/zed-industries-zeta-8bitMLX builds
4 on mlx-community| zed-industries-zeta-4bit | 4-bit | 4.3 GB | 7 GB | 72 |
|---|---|---|---|---|
| zed-industries-zeta-6bit | 6-bit | 6.2 GB | 9 GB | 58 |
| zed-industries-zeta-8bit | 8-bit | 8.1 GB | 12 GB | 102 |
| zed-industries-zeta-fp16 | fp16 | 15.2 GB | 20 GB | 35 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.