chaoliangUNSW · First MLX build 14 Oct 2026
Jev-Style-0.8B-Decision-v3
MLX
Text apache-2.0
A 752M parameter text classification model from chaoliangUNSW, with 2 MLX builds, from 8-bit to 16-bit.
- Parameters
- 752M From Hugging Face
- Quantisation
- 8-bit Jev-Style-0.8B-Decision-v3-mlx-8bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 800 MB Weights, estimated
- Downloads
- 284 This build, last 30 days
- Task
- Text classification Text
- 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/Jev-Style-0.8B-Decision-v3-mlx-8bitMLX builds
2 on mlx-community| Jev-Style-0.8B-Decision-v3-mlx-8bit | 8-bit | 800 MB | 3 GB | 284 |
|---|---|---|---|---|
| Jev-Style-0.8B-Decision-v3-mlx-16bit | 16-bit | 1.5 GB | 4 GB | 194 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.